Daily Papers

Are Capture-the-Flag competitions obsolete? In 2025, Cybersecurity AI (CAI) systematically conquered some of the world's most prestigious hacking competitions, achieving Rank #1 at multiple events and consistently outperforming thousands of human teams. Across five major circuits-HTB's AI vs Humans, Cyber Apocalypse (8,129 teams), Dragos OT CTF, UWSP Pointer Overflow, and the Neurogrid CTF showdown-CAI demonstrated that Jeopardy-style CTFs have become a solved game for well-engineered AI agents. At Neurogrid, CAI captured 41/45 flags to claim the 50,000 top prize; at Dragos OT, it sprinted 37% faster to 10K points than elite human teams; even when deliberately paused mid-competition, it maintained top-tier rankings. Critically, CAI achieved this dominance through our specialized alias1 model architecture, which delivers enterprise-scale AI security operations at unprecedented cost efficiency and with augmented autonomy-reducing 1B token inference costs from 5,940 to just $119, making continuous security agent operation financially viable for the first time. These results force an uncomfortable reckoning: if autonomous agents now dominate competitions designed to identify top security talent at negligible cost, what are CTFs actually measuring? This paper presents comprehensive evidence of AI capability across the 2025 CTF circuit and argues that the security community must urgently transition from Jeopardy-style contests to Attack & Defense formats that genuinely test adaptive reasoning and resilience-capabilities that remain uniquely human, for now.

The emergence of Large Language Models (LLMs) has significantly advanced solutions across various domains, from political science to software development. However, these models are constrained by their training data, which is static and limited to information available up to a specific date. Additionally, their generalized nature often necessitates fine-tuning -- whether for classification or instructional purposes -- to effectively perform specific downstream tasks. AI agents, leveraging LLMs as their core, mitigate some of these limitations by accessing external tools and real-time data, enabling applications such as live weather reporting and data analysis. In industrial settings, AI agents are transforming operations by enhancing decision-making, predictive maintenance, and process optimization. For example, in manufacturing, AI agents enable near-autonomous systems that boost productivity and support real-time decision-making. Despite these advancements, AI agents remain vulnerable to security threats, including prompt injection attacks, which pose significant risks to their integrity and reliability. To address these challenges, this paper proposes a framework for integrating Role-Based Access Control (RBAC) into AI agents, providing a robust security guardrail. This framework aims to support the effective and scalable deployment of AI agents, with a focus on on-premises implementations.

The rapid growth in the use of Large Language Models (LLMs) and AI Agents as part of software development and deployment is revolutionizing the information technology landscape. While code generation receives significant attention, a higher-impact application lies in using AI agents for operational resilience of cloud services, which currently require significant human effort and domain knowledge. There is a growing interest in AI for IT Operations (AIOps) which aims to automate complex operational tasks, like fault localization and root cause analysis, thereby reducing human intervention and customer impact. However, achieving the vision of autonomous and self-healing clouds though AIOps is hampered by the lack of standardized frameworks for building, evaluating, and improving AIOps agents. This vision paper lays the groundwork for such a framework by first framing the requirements and then discussing design decisions that satisfy them. We also propose AIOpsLab, a prototype implementation leveraging agent-cloud-interface that orchestrates an application, injects real-time faults using chaos engineering, and interfaces with an agent to localize and resolve the faults. We report promising results and lay the groundwork to build a modular and robust framework for building, evaluating, and improving agents for autonomous clouds.

This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising from the dynamic interactions among models, orchestrators, tools, and data within their operating environments. We propose a new way of identification of novel agentic risks through the lens of user safety. Although, for traditional LLMs and agentic models in isolation, safety and security has a clear separation, through the lens of safety in agentic systems, they appear to be connected. Building on this foundation, we define an operational agentic risk taxonomy that unifies traditional safety and security concerns with novel, uniquely agentic risks, including tool misuse, cascading action chains, and unintended control amplification among others. At the core of our approach is a dynamic agentic safety and security framework that operationalizes contextual agentic risk management by using auxiliary AI models and agents, with human oversight, to assist in contextual risk discovery, evaluation, and mitigation. We further address one of the most challenging aspects of safety and security of agentic systems: risk discovery through sandboxed, AI-driven red teaming. We demonstrate the framework effectiveness through a detailed case study of NVIDIA flagship agentic research assistant, AI-Q Research Assistant, showcasing practical, end-to-end safety and security evaluations in complex, enterprise-grade agentic workflows. This risk discovery phase finds novel agentic risks that are then contextually mitigated. We also release the dataset from our case study, containing traces of over 10,000 realistic attack and defense executions of the agentic workflow to help advance research in agentic safety.

The prospect of artificial intelligence (AI) competing in the adversarial landscape of cyber security has long been considered one of the most impactful, challenging, and potentially dangerous applications of AI. Here, we demonstrate a new approach to assessing AI's progress towards enabling and scaling real-world offensive cyber operations (OCO) tactics in use by modern threat actors. We detail OCCULT, a lightweight operational evaluation framework that allows cyber security experts to contribute to rigorous and repeatable measurement of the plausible cyber security risks associated with any given large language model (LLM) or AI employed for OCO. We also prototype and evaluate three very different OCO benchmarks for LLMs that demonstrate our approach and serve as examples for building benchmarks under the OCCULT framework. Finally, we provide preliminary evaluation results to demonstrate how this framework allows us to move beyond traditional all-or-nothing tests, such as those crafted from educational exercises like capture-the-flag environments, to contextualize our indicators and warnings in true cyber threat scenarios that present risks to modern infrastructure. We find that there has been significant recent advancement in the risks of AI being used to scale realistic cyber threats. For the first time, we find a model (DeepSeek-R1) is capable of correctly answering over 90% of challenging offensive cyber knowledge tests in our Threat Actor Competency Test for LLMs (TACTL) multiple-choice benchmarks. We also show how Meta's Llama and Mistral's Mixtral model families show marked performance improvements over earlier models against our benchmarks where LLMs act as offensive agents in MITRE's high-fidelity offensive and defensive cyber operations simulation environment, CyberLayer.

Information Technology (IT) Operations (Ops), particularly Artificial Intelligence for IT Operations (AIOps), is the guarantee for maintaining the orderly and stable operation of existing information systems. According to Gartner's prediction, the use of AI technology for automated IT operations has become a new trend. Large language models (LLMs) that have exhibited remarkable capabilities in NLP-related tasks, are showing great potential in the field of AIOps, such as in aspects of root cause analysis of failures, generation of operations and maintenance scripts, and summarizing of alert information. Nevertheless, the performance of current LLMs in Ops tasks is yet to be determined. In this paper, we present OpsEval, a comprehensive task-oriented Ops benchmark designed for LLMs. For the first time, OpsEval assesses LLMs' proficiency in various crucial scenarios at different ability levels. The benchmark includes 7184 multi-choice questions and 1736 question-answering (QA) formats in English and Chinese. By conducting a comprehensive performance evaluation of the current leading large language models, we show how various LLM techniques can affect the performance of Ops, and discussed findings related to various topics, including model quantification, QA evaluation, and hallucination issues. To ensure the credibility of our evaluation, we invite dozens of domain experts to manually review our questions. At the same time, we have open-sourced 20% of the test QA to assist current researchers in preliminary evaluations of their OpsLLM models. The remaining 80% of the data, which is not disclosed, is used to eliminate the issue of the test set leakage. Additionally, we have constructed an online leaderboard that is updated in real-time and will continue to be updated, ensuring that any newly emerging LLMs will be evaluated promptly. Both our dataset and leaderboard have been made public.

Traditional static cybersecurity models often struggle with scalability, real-time detection, and contextual responsiveness in the current digital product ecosystems which include cloud services, application programming interfaces (APIs), mobile platforms, and edge devices. This study introduces autonomous goal driven agents capable of dynamic learning and context-aware decision making as part of an adaptive cybersecurity architecture driven by agentic artificial intelligence (AI). To facilitate autonomous threat mitigation, proactive policy enforcement, and real-time anomaly detection, this framework integrates agentic AI across the key ecosystem layers. Behavioral baselining, decentralized risk scoring, and federated threat intelligence sharing are important features. The capacity of the system to identify zero-day attacks and dynamically modify access policies was demonstrated through native cloud simulations. The evaluation results show increased adaptability, decreased response latency, and improved detection accuracy. The architecture provides an intelligent and scalable blueprint for safeguarding complex digital infrastructure and is compatible with zero-trust models, thereby supporting the adherence to international cybersecurity regulations.

Artificial intelligence (AI), and especially its sub-field of Machine Learning (ML), are impacting the daily lives of everyone with their ubiquitous applications. In recent years, AI researchers and practitioners have introduced principles and guidelines to build systems that make reliable and trustworthy decisions. From a practical perspective, conventional ML systems process historical data to extract the features that are consequently used to train ML models that perform the desired task. However, in practice, a fundamental challenge arises when the system needs to be operationalized and deployed to evolve and operate in real-life environments continuously. To address this challenge, Machine Learning Operations (MLOps) have emerged as a potential recipe for standardizing ML solutions in deployment. Although MLOps demonstrated great success in streamlining ML processes, thoroughly defining the specifications of robust MLOps approaches remains of great interest to researchers and practitioners. In this paper, we provide a comprehensive overview of the trustworthiness property of MLOps systems. Specifically, we highlight technical practices to achieve robust MLOps systems. In addition, we survey the existing research approaches that address the robustness aspects of ML systems in production. We also review the tools and software available to build MLOps systems and summarize their support to handle the robustness aspects. Finally, we present the open challenges and propose possible future directions and opportunities within this emerging field. The aim of this paper is to provide researchers and practitioners working on practical AI applications with a comprehensive view to adopt robust ML solutions in production environments.

The Model Context Protocol (MCP), introduced by Anthropic, provides a standardized framework for artificial intelligence (AI) systems to interact with external data sources and tools in real-time. While MCP offers significant advantages for AI integration and capability extension, it introduces novel security challenges that demand rigorous analysis and mitigation. This paper builds upon foundational research into MCP architecture and preliminary security assessments to deliver enterprise-grade mitigation frameworks and detailed technical implementation strategies. Through systematic threat modeling and analysis of MCP implementations and analysis of potential attack vectors, including sophisticated threats like tool poisoning, we present actionable security patterns tailored for MCP implementers and adopters. The primary contribution of this research lies in translating theoretical security concerns into a practical, implementable framework with actionable controls, thereby providing essential guidance for the secure enterprise adoption and governance of integrated AI systems.

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic environments, especially under attack? To investigate, we ran the largest public red-teaming competition to date, targeting 22 frontier AI agents across 44 realistic deployment scenarios. Participants submitted 1.8 million prompt-injection attacks, with over 60,000 successfully eliciting policy violations such as unauthorized data access, illicit financial actions, and regulatory noncompliance. We use these results to build the Agent Red Teaming (ART) benchmark - a curated set of high-impact attacks - and evaluate it across 19 state-of-the-art models. Nearly all agents exhibit policy violations for most behaviors within 10-100 queries, with high attack transferability across models and tasks. Importantly, we find limited correlation between agent robustness and model size, capability, or inference-time compute, suggesting that additional defenses are needed against adversarial misuse. Our findings highlight critical and persistent vulnerabilities in today's AI agents. By releasing the ART benchmark and accompanying evaluation framework, we aim to support more rigorous security assessment and drive progress toward safer agent deployment.

AIOps (Artificial Intelligence for IT Operations) solutions leverage the tremendous amount of data produced during the operation of large-scale systems and machine learning models to assist software practitioners in their system operations. Existing AIOps solutions usually maintain AIOps models against concept drift through periodical retraining, despite leaving a pile of discarded historical models that may perform well on specific future data. Other prior works propose dynamically selecting models for prediction tasks from a set of candidate models to optimize the model performance. However, there is no prior work in the AIOps area that assesses the use of model selection mechanisms on historical models to improve model performance or robustness. To fill the gap, we evaluate several model selection mechanisms by assessing their capabilities in selecting the optimal AIOps models that were built in the past to make predictions for the target data. We performed a case study on three large-scale public operation datasets: two trace datasets from the cloud computing platforms of Google and Alibaba, and one disk stats dataset from the BackBlaze cloud storage data center. We observe that the model selection mechnisms utilizing temporal adjacency tend to have a better performance and can prevail the periodical retraining approach. Our findings also highlight a performance gap between existing model selection mechnisms and the theoretical upper bound which may motivate future researchers and practitioners in investigating more efficient and effective model selection mechanisms that fit in the context of AIOps.

This paper explores the rapidly evolving ecosystem of publicly available AI models, and their potential implications on the security and safety landscape. As AI models become increasingly prevalent, understanding their potential risks and vulnerabilities is crucial. We review the current security and safety scenarios while highlighting challenges such as tracking issues, remediation, and the apparent absence of AI model lifecycle and ownership processes. Comprehensive strategies to enhance security and safety for both model developers and end-users are proposed. This paper aims to provide some of the foundational pieces for more standardized security, safety, and transparency in the development and operation of AI models and the larger open ecosystems and communities forming around them.

AI assistants produce vulnerable code in 45% of security-relevant scenarios, introducing flaws into production systems at scale. Yet existing secure coding datasets fall short. They lack incident grounding, don't provide the scale modern training requires, and miss the operational security context developers need for production deployments. We present SecureCode v2.0, a production-grade dataset of 1,215 security-focused coding examples that passed structural validation and expert security review. Every example ties to actual documented security incidents with CVE references, provides vulnerable and secure implementations, demonstrates concrete attacks, and includes defense-in-depth operational guidance. The dataset covers 11 vulnerability categories (complete OWASP Top 10:2025 plus AI/ML Security Threats) across 11 languages (Python, JavaScript, Java, Go, PHP, C#, TypeScript, Ruby, Rust, Kotlin, and YAML for infrastructure-as-code). Our quality assurance framework ensures complete incident grounding. Each example includes SIEM integration strategies, infrastructure hardening recommendations (Docker, AppArmor, WAF configurations), and testing approaches using language-appropriate frameworks. The dataset uses a 4-turn conversational structure mirroring actual developer-AI interactions, escalating from basic implementations to advanced security considerations and defense-in-depth guidance. Our contributions: (1) 1,215 rigorously validated examples split into 989 training, 122 validation, and 104 test sets, (2) an automated validation framework ensuring dataset consistency, (3) a 4-turn conversational structure capturing realistic security workflows, (4) comprehensive operational security guidance with SIEM integration strategies, (5) complete language-specific implementation fidelity, and (6) open-source release of data, validation tools, and benchmarking protocols.

Agentic AI systems, built on large language models (LLMs) and deployed in multi-agent configurations, are redefining intelligent autonomy, collaboration and decision-making across enterprise and societal domains. This review presents a structured analysis of Trust, Risk, and Security Management (TRiSM) in the context of LLM-based agentic multi-agent systems (AMAS). We begin by examining the conceptual foundations of agentic AI, its architectural differences from traditional AI agents, and the emerging system designs that enable scalable, tool-using autonomy. The TRiSM in the agentic AI framework is then detailed through four pillars governance, explainability, ModelOps, and privacy/security each contextualized for agentic LLMs. We identify unique threat vectors and introduce a comprehensive risk taxonomy for the agentic AI applications, supported by case studies illustrating real-world vulnerabilities. Furthermore, the paper also surveys trust-building mechanisms, transparency and oversight techniques, and state-of-the-art explainability strategies in distributed LLM agent systems. Additionally, metrics for evaluating trust, interpretability, and human-centered performance are reviewed alongside open benchmarking challenges. Security and privacy are addressed through encryption, adversarial defense, and compliance with evolving AI regulations. The paper concludes with a roadmap for responsible agentic AI, proposing research directions to align emerging multi-agent systems with robust TRiSM principles for safe, accountable, and transparent deployment.

The rapid advancement of Generative AI has catalyzed the emergence of autonomous AI agents, presenting unprecedented challenges for enterprise computing infrastructures. Current enterprise API architectures are predominantly designed for human-driven, predefined interaction patterns, rendering them ill-equipped to support intelligent agents' dynamic, goal-oriented behaviors. This research systematically examines the architectural adaptations for enterprise APIs to support AI agentic workflows effectively. Through a comprehensive analysis of existing API design paradigms, agent interaction models, and emerging technological constraints, the paper develops a strategic framework for API transformation. The study employs a mixed-method approach, combining theoretical modeling, comparative analysis, and exploratory design principles to address critical challenges in standardization, performance, and intelligent interaction. The proposed research contributes a conceptual model for next-generation enterprise APIs that can seamlessly integrate with autonomous AI agent ecosystems, offering significant implications for future enterprise computing architectures.

Cloud Operations (CloudOps) is a rapidly growing field focused on the automated management and optimization of cloud infrastructure which is essential for organizations navigating increasingly complex cloud environments. MontyCloud Inc. is one of the major companies in the CloudOps domain that leverages autonomous bots to manage cloud compliance, security, and continuous operations. To make the platform more accessible and effective to the customers, we leveraged the use of GenAI. Developing a GenAI-based solution for autonomous CloudOps for the existing MontyCloud system presented us with various challenges such as i) diverse data sources; ii) orchestration of multiple processes; and iii) handling complex workflows to automate routine tasks. To this end, we developed MOYA, a multi-agent framework that leverages GenAI and balances autonomy with the necessary human control. This framework integrates various internal and external systems and is optimized for factors like task orchestration, security, and error mitigation while producing accurate, reliable, and relevant insights by utilizing Retrieval Augmented Generation (RAG). Evaluations of our multi-agent system with the help of practitioners as well as using automated checks demonstrate enhanced accuracy, responsiveness, and effectiveness over non-agentic approaches across complex workflows.

Industrial processes must be robust and adaptable, as environments and tasks are often unpredictable, while operational errors remain costly and difficult to detect. AI-based control systems offer a path forward, yet typically depend on supervised learning with extensive labelled datasets, which limits their ability to generalize across variable and data-scarce industrial settings. Foundation models could enable broader reasoning and knowledge integration, but rarely deliver the quantitative precision demanded by engineering applications. Here, we introduceControl and Interpretation of Production via Hybrid Expertise and Reasoning (CIPHER): a vision-language-action (VLA) model framework aiming to replicate human-like reasoning for industrial control, instantiated in a commercial-grade 3D printer. It integrates a process expert, a regression model enabling quantitative characterization of system states required for engineering tasks. CIPHER also incorporates retrieval-augmented generation to access external expert knowledge and support physics-informed, chain-of-thought reasoning. This hybrid architecture exhibits strong generalization to out-of-distribution tasks. It interprets visual or textual inputs from process monitoring, explains its decisions, and autonomously generates precise machine instructions, without requiring explicit annotations. CIPHER thus lays the foundations for autonomous systems that act with precision, reason with context, and communicate decisions transparently, supporting safe and trusted deployment in industrial settings.

The AI trustworthiness crisis threatens to derail the artificial intelligence revolution, with regulatory barriers, security vulnerabilities, and accountability gaps preventing deployment in critical domains. Current AI systems operate on opaque data structures that lack the audit trails, provenance tracking, or explainability required by emerging regulations like the EU AI Act. We propose an artifact-centric AI agent paradigm where behavior is driven by persistent, verifiable data artifacts rather than ephemeral tasks, solving the trustworthiness problem at the data architecture level. Central to this approach is the Multimodal Artifact File Format (MAIF), an AI-native container embedding semantic representations, cryptographic provenance, and granular access controls. MAIF transforms data from passive storage into active trust enforcement, making every AI operation inherently auditable. Our production-ready implementation demonstrates ultra-high-speed streaming (2,720.7 MB/s), optimized video processing (1,342 MB/s), and enterprise-grade security. Novel algorithms for cross-modal attention, semantic compression, and cryptographic binding achieve up to 225 compression while maintaining semantic fidelity. Advanced security features include stream-level access control, real-time tamper detection, and behavioral anomaly analysis with minimal overhead. This approach directly addresses the regulatory, security, and accountability challenges preventing AI deployment in sensitive domains, offering a viable path toward trustworthy AI systems at scale.

As frontier AI advances rapidly, understanding its impact on cybersecurity and inherent risks is essential to ensuring safe AI evolution (e.g., guiding risk mitigation and informing policymakers). While some studies review AI applications in cybersecurity, none of them comprehensively discuss AI's future impacts or provide concrete recommendations for navigating its safe and secure usage. This paper presents an in-depth analysis of frontier AI's impact on cybersecurity and establishes a systematic framework for risk assessment and mitigation. To this end, we first define and categorize the marginal risks of frontier AI in cybersecurity and then systemically analyze the current and future impacts of frontier AI in cybersecurity, qualitatively and quantitatively. We also discuss why frontier AI likely benefits attackers more than defenders in the short term from equivalence classes, asymmetry, and economic impact. Next, we explore frontier AI's impact on future software system development, including enabling complex hybrid systems while introducing new risks. Based on our findings, we provide security recommendations, including constructing fine-grained benchmarks for risk assessment, designing AI agents for defenses, building security mechanisms and provable defenses for hybrid systems, enhancing pre-deployment security testing and transparency, and strengthening defenses for users. Finally, we present long-term research questions essential for understanding AI's future impacts and unleashing its defensive capabilities.

Enterprise Resource Planning (ERP) systems serve as the digital backbone of modern financial institutions, yet they continue to rely on static, rule-based workflows that limit adaptability, scalability, and intelligence. As business operations grow more complex and data-rich, conventional ERP platforms struggle to integrate structured and unstructured data in real time and to accommodate dynamic, cross-functional workflows. In this paper, we present the first AI-native, agent-based framework for ERP systems, introducing a novel architecture of Generative Business Process AI Agents (GBPAs) that bring autonomy, reasoning, and dynamic optimization to enterprise workflows. The proposed system integrates generative AI with business process modeling and multi-agent orchestration, enabling end-to-end automation of complex tasks such as budget planning, financial reporting, and wire transfer processing. Unlike traditional workflow engines, GBPAs interpret user intent, synthesize workflows in real time, and coordinate specialized sub-agents for modular task execution. We validate the framework through case studies in bank wire transfers and employee reimbursements, two representative financial workflows with distinct complexity and data modalities. Results show that GBPAs achieve up to 40% reduction in processing time, 94% drop in error rate, and improved regulatory compliance by enabling parallelism, risk control insertion, and semantic reasoning. These findings highlight the potential of GBPAs to bridge the gap between generative AI capabilities and enterprise-grade automation, laying the groundwork for the next generation of intelligent ERP systems.

Agentic AI systems capable of reasoning, planning, and executing actions present fundamentally distinct governance challenges compared to traditional AI models. Unlike conventional AI, these systems exhibit emergent and unexpected behaviors during runtime, introducing novel agent-related risks that cannot be fully anticipated through pre-deployment governance alone. To address this critical gap, we introduce MI9, the first fully integrated runtime governance framework designed specifically for safety and alignment of agentic AI systems. MI9 introduces real-time controls through six integrated components: agency-risk index, agent-semantic telemetry capture, continuous authorization monitoring, Finite-State-Machine (FSM)-based conformance engines, goal-conditioned drift detection, and graduated containment strategies. Operating transparently across heterogeneous agent architectures, MI9 enables the systematic, safe, and responsible deployment of agentic systems in production environments where conventional governance approaches fall short, providing the foundational infrastructure for safe agentic AI deployment at scale. Detailed analysis through a diverse set of scenarios demonstrates MI9's systematic coverage of governance challenges that existing approaches fail to address, establishing the technical foundation for comprehensive agentic AI oversight.

We explore the feasibility and effectiveness of using LLM-driven autonomous systems for Assumed Breach penetration testing in enterprise networks. We introduce a novel prototype that, driven by Large Language Models (LLMs), can compromise accounts within a real-life Active Directory testbed. Our research provides a comprehensive evaluation of the prototype's capabilities, and highlights both strengths and limitations while executing attack. The evaluation uses a realistic simulation environment (Game of Active Directory, GOAD) to capture intricate interactions, stochastic outcomes, and timing dependencies that characterize live network scenarios. The study concludes that autonomous LLMs are able to conduct Assumed Breach simulations, potentially democratizing access to penetration testing for organizations facing budgetary constraints. The prototype's source code, traces, and analyzed logs are released as open-source to enhance collective cybersecurity and facilitate future research in LLM-driven cybersecurity automation.

AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates security modeling, while the integration of traditional software with AI components entangles novel LLM vulnerabilities with conventional security risks. Existing frameworks only partially address these challenges as they either capture specific vulnerabilities only or require modeling of complete agents. To address these limitations, we introduce threat snapshots: a framework that isolates specific states in an agent's execution flow where LLM vulnerabilities manifest, enabling the systematic identification and categorization of security risks that propagate from the LLM to the agent level. We apply this framework to construct the b^3 benchmark, a security benchmark based on 194331 unique crowdsourced adversarial attacks. We then evaluate 31 popular LLMs with it, revealing, among other insights, that enhanced reasoning capabilities improve security, while model size does not correlate with security. We release our benchmark, dataset, and evaluation code to facilitate widespread adoption by LLM providers and practitioners, offering guidance for agent developers and incentivizing model developers to prioritize backbone security improvements.

Computer-use agent (CUA) frameworks, powered by large language models (LLMs) or multimodal LLMs (MLLMs), are rapidly maturing as assistants that can perceive context, reason, and act directly within software environments. Among their most critical applications is operating system (OS) control. As CUAs in the OS domain become increasingly embedded in daily operations, it is imperative to examine their real-world security implications, specifically whether CUAs can be misused to perform realistic, security-relevant attacks. Existing works exhibit four major limitations: Missing attacker-knowledge model on tactics, techniques, and procedures (TTP), Incomplete coverage for end-to-end kill chains, unrealistic environment without multi-host and encrypted user credentials, and unreliable judgment dependent on LLM-as-a-Judge. To address these gaps, we propose AdvCUA, the first benchmark aligned with real-world TTPs in MITRE ATT&CK Enterprise Matrix, which comprises 140 tasks, including 40 direct malicious tasks, 74 TTP-based malicious tasks, and 26 end-to-end kill chains, systematically evaluates CUAs under a realistic enterprise OS security threat in a multi-host environment sandbox by hard-coded evaluation. We evaluate the existing five mainstream CUAs, including ReAct, AutoGPT, Gemini CLI, Cursor CLI, and Cursor IDE based on 8 foundation LLMs. The results demonstrate that current frontier CUAs do not adequately cover OS security-centric threats. These capabilities of CUAs reduce dependence on custom malware and deep domain expertise, enabling even inexperienced attackers to mount complex enterprise intrusions, which raises social concern about the responsibility and security of CUAs.

This paper analyzes Large Language Model (LLM) security vulnerabilities based on data from Crucible, encompassing 214,271 attack attempts by 1,674 users across 30 LLM challenges. Our findings reveal automated approaches significantly outperform manual techniques (69.5% vs 47.6% success rate), despite only 5.2% of users employing automation. We demonstrate that automated approaches excel in systematic exploration and pattern matching challenges, while manual approaches retain speed advantages in certain creative reasoning scenarios, often solving problems 5x faster when successful. Challenge categories requiring systematic exploration are most effectively targeted through automation, while intuitive challenges sometimes favor manual techniques for time-to-solve metrics. These results illuminate how algorithmic testing is transforming AI red-teaming practices, with implications for both offensive security research and defensive measures. Our analysis suggests optimal security testing combines human creativity for strategy development with programmatic execution for thorough exploration.

The rapid growth of large-scale AI models, particularly large language models has brought significant challenges in data privacy, computational resources, and accessibility. Traditional centralized architectures often struggle to meet required data security and scalability needs which hinders the democratization of AI systems. Nesa introduces a model-agnostic sharding framework designed for decentralized AI inference. Our framework uses blockchain-based sequential deep neural network sharding to distribute computational tasks across a diverse network of nodes based on a personalised heuristic and routing mechanism. This enables efficient distributed training and inference for recent large-scale models even on consumer-grade hardware. We use compression techniques like dynamic blockwise quantization and mixed matrix decomposition to reduce data transfer and memory needs. We also integrate robust security measures, including hardware-based trusted execution environments to ensure data integrity and confidentiality. Evaluating our system across various natural language processing and vision tasks shows that these compression strategies do not compromise model accuracy. Our results highlight the potential to democratize access to cutting-edge AI technologies by enabling secure and efficient inference on a decentralized network.

We present the first comprehensive evaluation of AI agents against human cybersecurity professionals in a live enterprise environment. We evaluate ten cybersecurity professionals alongside six existing AI agents and ARTEMIS, our new agent scaffold, on a large university network consisting of ~8,000 hosts across 12 subnets. ARTEMIS is a multi-agent framework featuring dynamic prompt generation, arbitrary sub-agents, and automatic vulnerability triaging. In our comparative study, ARTEMIS placed second overall, discovering 9 valid vulnerabilities with an 82% valid submission rate and outperforming 9 of 10 human participants. While existing scaffolds such as Codex and CyAgent underperformed relative to most human participants, ARTEMIS demonstrated technical sophistication and submission quality comparable to the strongest participants. We observe that AI agents offer advantages in systematic enumeration, parallel exploitation, and cost -- certain ARTEMIS variants cost 18/hour versus 60/hour for professional penetration testers. We also identify key capability gaps: AI agents exhibit higher false-positive rates and struggle with GUI-based tasks.

The risks of frontier AI may require international cooperation, which in turn may require verification: checking that all parties follow agreed-on rules. For instance, states might need to verify that powerful AI models are widely deployed only after their risks to international security have been evaluated and deemed manageable. However, research on AI verification could benefit from greater clarity and detail. To address this, this report provides an in-depth overview of AI verification, intended for both policy professionals and technical researchers. We present novel conceptual frameworks, detailed implementation options, and key R&D challenges. These draw on existing literature, expert interviews, and original analysis, all within the scope of confidentially overseeing AI development and deployment that uses thousands of high-end AI chips. We find that states could eventually verify compliance by using six largely independent verification approaches with substantial redundancy: (1) built-in security features in AI chips; (2-3) separate monitoring devices attached to AI chips; and (4-6) personnel-based mechanisms, such as whistleblower programs. While promising, these approaches require guardrails to protect against abuse and power concentration, and many of these technologies have yet to be built or stress-tested. To enable states to confidently verify compliance with rules on large-scale AI development and deployment, the R&D challenges we list need significant progress.

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces have dramatically expanded capabilities for real-time data retrieval, complex computation, and multi-step orchestration. Yet, the explosive proliferation of plugins, connectors, and inter-agent protocols has outpaced discovery mechanisms and security practices, resulting in brittle integrations vulnerable to diverse threats. In this survey, we introduce the first unified, end-to-end threat model for LLM-agent ecosystems, spanning host-to-tool and agent-to-agent communications, formalize adversary capabilities and attacker objectives, and catalog over thirty attack techniques. Specifically, we organized the threat model into four domains: Input Manipulation (e.g., prompt injections, long-context hijacks, multimodal adversarial inputs), Model Compromise (e.g., prompt- and parameter-level backdoors, composite and encrypted multi-backdoors, poisoning strategies), System and Privacy Attacks (e.g., speculative side-channels, membership inference, retrieval poisoning, social-engineering simulations), and Protocol Vulnerabilities (e.g., exploits in Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent Network Protocol (ANP), and Agent-to-Agent (A2A) protocol). For each category, we review representative scenarios, assess real-world feasibility, and evaluate existing defenses. Building on our threat taxonomy, we identify key open challenges and future research directions, such as securing MCP deployments through dynamic trust management and cryptographic provenance tracking; designing and hardening Agentic Web Interfaces; and achieving resilience in multi-agent and federated environments. Our work provides a comprehensive reference to guide the design of robust defense mechanisms and establish best practices for resilient LLM-agent workflows.

Creating secure and resilient applications with large language models (LLM) requires anticipating, adjusting to, and countering unforeseen threats. Red-teaming has emerged as a critical technique for identifying vulnerabilities in real-world LLM implementations. This paper presents a detailed threat model and provides a systematization of knowledge (SoK) of red-teaming attacks on LLMs. We develop a taxonomy of attacks based on the stages of the LLM development and deployment process and extract various insights from previous research. In addition, we compile methods for defense and practical red-teaming strategies for practitioners. By delineating prominent attack motifs and shedding light on various entry points, this paper provides a framework for improving the security and robustness of LLM-based systems.

In recent years, AI red teaming has emerged as a practice for probing the safety and security of generative AI systems. Due to the nascency of the field, there are many open questions about how red teaming operations should be conducted. Based on our experience red teaming over 100 generative AI products at Microsoft, we present our internal threat model ontology and eight main lessons we have learned: 1. Understand what the system can do and where it is applied 2. You don't have to compute gradients to break an AI system 3. AI red teaming is not safety benchmarking 4. Automation can help cover more of the risk landscape 5. The human element of AI red teaming is crucial 6. Responsible AI harms are pervasive but difficult to measure 7. LLMs amplify existing security risks and introduce new ones 8. The work of securing AI systems will never be complete By sharing these insights alongside case studies from our operations, we offer practical recommendations aimed at aligning red teaming efforts with real world risks. We also highlight aspects of AI red teaming that we believe are often misunderstood and discuss open questions for the field to consider.

The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a wide range of applications, including conversational AI, recommendation systems, autonomous driving, content generation, medical diagnostics, and scientific discovery. However, their widespread deployment also exposes them to significant safety risks, raising concerns about robustness, reliability, and ethical implications. This survey provides a systematic review of current safety research on large models, covering Vision Foundation Models (VFMs), Large Language Models (LLMs), Vision-Language Pre-training (VLP) models, Vision-Language Models (VLMs), Diffusion Models (DMs), and large-model-based Agents. Our contributions are summarized as follows: (1) We present a comprehensive taxonomy of safety threats to these models, including adversarial attacks, data poisoning, backdoor attacks, jailbreak and prompt injection attacks, energy-latency attacks, data and model extraction attacks, and emerging agent-specific threats. (2) We review defense strategies proposed for each type of attacks if available and summarize the commonly used datasets and benchmarks for safety research. (3) Building on this, we identify and discuss the open challenges in large model safety, emphasizing the need for comprehensive safety evaluations, scalable and effective defense mechanisms, and sustainable data practices. More importantly, we highlight the necessity of collective efforts from the research community and international collaboration. Our work can serve as a useful reference for researchers and practitioners, fostering the ongoing development of comprehensive defense systems and platforms to safeguard AI models.

Large Language Models (LLMs) show promise in generating firmware for embedded systems, but often introduce security flaws and fail to meet real-time performance constraints. This paper proposes a three-phase methodology that combines LLM-based firmware generation with automated security validation and iterative refinement in a virtualized environment. Using structured prompts, models like GPT-4 generate firmware for networking and control tasks, deployed on FreeRTOS via QEMU. These implementations are tested using fuzzing, static analysis, and runtime monitoring to detect vulnerabilities such as buffer overflows (CWE-120), race conditions (CWE-362), and denial-of-service threats (CWE-400). Specialized AI agents for Threat Detection, Performance Optimization, and Compliance Verification collaborate to improve detection and remediation. Identified issues are categorized using CWE, then used to prompt targeted LLM-generated patches in an iterative loop. Experiments show a 92.4\% Vulnerability Remediation Rate (37.3\% improvement), 95.8\% Threat Model Compliance, and 0.87 Security Coverage Index. Real-time metrics include 8.6ms worst-case execution time and 195μs jitter. This process enhances firmware security and performance while contributing an open-source dataset for future research.

The rapid integration of agentic AI into high-stakes real-world applications requires robust oversight mechanisms. The emerging field of AI Control (AIC) aims to provide such an oversight mechanism, but practical adoption depends heavily on implementation overhead. To study this problem better, we introduce the notion of Control tax -- the operational and financial cost of integrating control measures into AI pipelines. Our work makes three key contributions to the field of AIC: (1) we introduce a theoretical framework that quantifies the Control Tax and maps classifier performance to safety assurances; (2) we conduct comprehensive evaluations of state-of-the-art language models in adversarial settings, where attacker models insert subtle backdoors into code while monitoring models attempt to detect these vulnerabilities; and (3) we provide empirical financial cost estimates for control protocols and develop optimized monitoring strategies that balance safety and cost-effectiveness while accounting for practical constraints like auditing budgets. Our framework enables practitioners to make informed decisions by systematically connecting safety guarantees with their costs, advancing AIC through principled economic feasibility assessment across different deployment contexts.

As software systems grow increasingly intricate, Artificial Intelligence for IT Operations (AIOps) methods have been widely used in software system failure management to ensure the high availability and reliability of large-scale distributed software systems. However, these methods still face several challenges, such as lack of cross-platform generality and cross-task flexibility. Fortunately, recent advancements in large language models (LLMs) can significantly address these challenges, and many approaches have already been proposed to explore this field. However, there is currently no comprehensive survey that discusses the differences between LLM-based AIOps and traditional AIOps methods. Therefore, this paper presents a comprehensive survey of AIOps technology for failure management in the LLM era. It includes a detailed definition of AIOps tasks for failure management, the data sources for AIOps, and the LLM-based approaches adopted for AIOps. Additionally, this survey explores the AIOps subtasks, the specific LLM-based approaches suitable for different AIOps subtasks, and the challenges and future directions of the domain, aiming to further its development and application.

To reduce development overhead and enable seamless integration between potential components comprising any given generative AI application, the Model Context Protocol (MCP) (Anthropic, 2024) has recently been released and subsequently widely adopted. The MCP is an open protocol that standardizes API calls to large language models (LLMs), data sources, and agentic tools. By connecting multiple MCP servers, each defined with a set of tools, resources, and prompts, users are able to define automated workflows fully driven by LLMs. However, we show that the current MCP design carries a wide range of security risks for end users. In particular, we demonstrate that industry-leading LLMs may be coerced into using MCP tools to compromise an AI developer's system through various attacks, such as malicious code execution, remote access control, and credential theft. To proactively mitigate these and related attacks, we introduce a safety auditing tool, MCPSafetyScanner, the first agentic tool to assess the security of an arbitrary MCP server. MCPScanner uses several agents to (a) automatically determine adversarial samples given an MCP server's tools and resources; (b) search for related vulnerabilities and remediations based on those samples; and (c) generate a security report detailing all findings. Our work highlights serious security issues with general-purpose agentic workflows while also providing a proactive tool to audit MCP server safety and address detected vulnerabilities before deployment. The described MCP server auditing tool, MCPSafetyScanner, is freely available at: https://github.com/johnhalloran321/mcpSafetyScanner

From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong capability is bound with a similar threat: the security and research community must build up its models before the approach is leveraged by malicious actors for cybercrime. We therefore propose and evaluate RedTeamLLM, an integrated architecture with a comprehensive security model for automatization of pentest tasks. RedTeamLLM follows three key steps: summarizing, reasoning and act, which embed its operational capacity. This novel framework addresses four open challenges: plan correction, memory management, context window constraint, and generality vs. specialization. Evaluation is performed through the automated resolution of a range of entry-level, but not trivial, CTF challenges. The contribution of the reasoning capability of our agentic AI framework is specifically evaluated.

As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation challenging and critical. Existing red-teaming efforts are either restricted to a narrow set of adversarial patterns or depend heavily on manual engineering, lacking scalable exploration of emerging real-world VLM vulnerabilities. To bridge this gap, we propose ARMs, an adaptive red-teaming agent that systematically conducts comprehensive risk assessments for VLMs. Given a target harmful behavior or risk definition, ARMs automatically optimizes diverse red-teaming strategies with reasoning-enhanced multi-step orchestration, to effectively elicit harmful outputs from target VLMs. We propose 11 novel multimodal attack strategies, covering diverse adversarial patterns of VLMs (e.g., reasoning hijacking, contextual cloaking), and integrate 17 red-teaming algorithms into ARMs via model context protocol (MCP). To balance the diversity and effectiveness of the attack, we design a layered memory with an epsilon-greedy attack exploration algorithm. Extensive experiments on instance- and policy-based benchmarks show that ARMs achieves SOTA attack success rates, exceeding baselines by an average of 52.1% and surpassing 90% on Claude-4-Sonnet. We show that the diversity of red-teaming instances generated by ARMs is significantly higher, revealing emerging vulnerabilities in VLMs. Leveraging ARMs, we construct ARMs-Bench, a large-scale multimodal safety dataset comprising over 30K red-teaming instances spanning 51 diverse risk categories, grounded in both real-world multimodal threats and regulatory risks. Safety fine-tuning with ARMs-Bench substantially improves the robustness of VLMs while preserving their general utility, providing actionable guidance to improve multimodal safety alignment against emerging threats.

AI coding assistants like GitHub Copilot are rapidly transforming software development, but their safety remains deeply uncertain-especially in high-stakes domains like cybersecurity. Current red-teaming tools often rely on fixed benchmarks or unrealistic prompts, missing many real-world vulnerabilities. We present ASTRA, an automated agent system designed to systematically uncover safety flaws in AI-driven code generation and security guidance systems. ASTRA works in three stages: (1) it builds structured domain-specific knowledge graphs that model complex software tasks and known weaknesses; (2) it performs online vulnerability exploration of each target model by adaptively probing both its input space, i.e., the spatial exploration, and its reasoning processes, i.e., the temporal exploration, guided by the knowledge graphs; and (3) it generates high-quality violation-inducing cases to improve model alignment. Unlike prior methods, ASTRA focuses on realistic inputs-requests that developers might actually ask-and uses both offline abstraction guided domain modeling and online domain knowledge graph adaptation to surface corner-case vulnerabilities. Across two major evaluation domains, ASTRA finds 11-66% more issues than existing techniques and produces test cases that lead to 17% more effective alignment training, showing its practical value for building safer AI systems.

AI-powered development platforms are making software creation accessible to a broader audience, but this democratization has triggered a scalability crisis in security auditing. With studies showing that up to 40% of AI-generated code contains vulnerabilities, the pace of development now vastly outstrips the capacity for thorough security assessment. We present MAPTA, a multi-agent system for autonomous web application security assessment that combines large language model orchestration with tool-grounded execution and end-to-end exploit validation. On the 104-challenge XBOW benchmark, MAPTA achieves 76.9% overall success with perfect performance on SSRF and misconfiguration vulnerabilities, 83% success on broken authorization, and strong results on injection attacks including server-side template injection (85%) and SQL injection (83%). Cross-site scripting (57%) and blind SQL injection (0%) remain challenging. Our comprehensive cost analysis across all challenges totals 21.38 with a median cost of 0.073 for successful attempts versus 0.357 for failures. Success correlates strongly with resource efficiency, enabling practical early-stopping thresholds at approximately 40 tool calls or 0.30 per challenge. MAPTA's real-world findings are impactful given both the popularity of the respective scanned GitHub repositories (8K-70K stars) and MAPTA's low average operating cost of $3.67 per open-source assessment: MAPTA discovered critical vulnerabilities including RCEs, command injections, secret exposure, and arbitrary file write vulnerabilities. Findings are responsibly disclosed, 10 findings are under CVE review.

Large Language Models (LLMs) have gained widespread popularity across diverse domains involving text generation, summarization, and various natural language processing tasks. Despite their inherent limitations, LLM-based designs have shown promising capabilities in planning and navigating open-world scenarios. This paper introduces a novel application of pre-trained LLMs as agents within cybersecurity network environments, focusing on their utility for sequential decision-making processes. We present an approach wherein pre-trained LLMs are leveraged as attacking agents in two reinforcement learning environments. Our proposed agents demonstrate similar or better performance against state-of-the-art agents trained for thousands of episodes in most scenarios and configurations. In addition, the best LLM agents perform similarly to human testers of the environment without any additional training process. This design highlights the potential of LLMs to efficiently address complex decision-making tasks within cybersecurity. Furthermore, we introduce a new network security environment named NetSecGame. The environment is designed to eventually support complex multi-agent scenarios within the network security domain. The proposed environment mimics real network attacks and is designed to be highly modular and adaptable for various scenarios.

The rapid evolution of artificial intelligence (AI) has ushered in a new era of integrated systems that merge computational prowess with human decision-making. In this paper, we introduce the concept of Orchestrated Distributed Intelligence (ODI), a novel paradigm that reconceptualizes AI not as isolated autonomous agents, but as cohesive, orchestrated networks that work in tandem with human expertise. ODI leverages advanced orchestration layers, multi-loop feedback mechanisms, and a high cognitive density framework to transform static, record-keeping systems into dynamic, action-oriented environments. Through a comprehensive review of multi-agent system literature, recent technological advances, and practical insights from industry forums, we argue that the future of AI lies in integrating distributed intelligence within human-centric workflows. This approach not only enhances operational efficiency and strategic agility but also addresses challenges related to scalability, transparency, and ethical decision-making. Our work outlines key theoretical implications and presents a practical roadmap for future research and enterprise innovation, aiming to pave the way for responsible and adaptive AI systems that drive sustainable innovation in human organizations.

The rapid advancement of ML models in critical sectors such as healthcare, finance, and security has intensified the need for robust data security, model integrity, and reliable outputs. Large multimodal foundational models, while crucial for complex tasks, present challenges in scalability, reliability, and potential misuse. Decentralized systems offer a solution by distributing workload and mitigating central points of failure, but they introduce risks of unauthorized access to sensitive data across nodes. We address these challenges with a comprehensive framework designed for responsible AI development. Our approach incorporates: 1) Zero-knowledge proofs for secure model verification, enhancing trust without compromising privacy. 2) Consensus-based verification checks to ensure consistent outputs across nodes, mitigating hallucinations and maintaining model integrity. 3) Split Learning techniques that segment models across different nodes, preserving data privacy by preventing full data access at any point. 4) Hardware-based security through trusted execution environments (TEEs) to protect data and computations. This framework aims to enhance security and privacy and improve the reliability and fairness of multimodal AI systems. Promoting efficient resource utilization contributes to more sustainable AI development. Our state-of-the-art proofs and principles demonstrate the framework's effectiveness in responsibly democratizing artificial intelligence, offering a promising approach for building secure and private foundational models.

Successful defense against dynamically evolving cyber threats requires advanced and sophisticated techniques. This research presents a novel approach to enhance real-time cybersecurity threat detection and response by integrating large language models (LLMs) and Retrieval-Augmented Generation (RAG) systems with continuous threat intelligence feeds. Leveraging recent advancements in LLMs, specifically GPT-4o, and the innovative application of RAG techniques, our approach addresses the limitations of traditional static threat analysis by incorporating dynamic, real-time data sources. We leveraged RAG to get the latest information in real-time for threat intelligence, which is not possible in the existing GPT-4o model. We employ the Patrowl framework to automate the retrieval of diverse cybersecurity threat intelligence feeds, including Common Vulnerabilities and Exposures (CVE), Common Weakness Enumeration (CWE), Exploit Prediction Scoring System (EPSS), and Known Exploited Vulnerabilities (KEV) databases, and integrate these with the all-mpnet-base-v2 model for high-dimensional vector embeddings, stored and queried in Milvus. We demonstrate our system's efficacy through a series of case studies, revealing significant improvements in addressing recently disclosed vulnerabilities, KEVs, and high-EPSS-score CVEs compared to the baseline GPT-4o. This work not only advances the role of LLMs in cybersecurity but also establishes a robust foundation for the development of automated intelligent cyberthreat information management systems, addressing crucial gaps in current cybersecurity practices.

The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e.g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs. To address this gap, this paper introduces, for the first time, the concept of "full-stack" safety to systematically consider safety issues throughout the entire process of LLM training, deployment, and eventual commercialization. Compared to the off-the-shelf LLM safety surveys, our work demonstrates several distinctive advantages: (I) Comprehensive Perspective. We define the complete LLM lifecycle as encompassing data preparation, pre-training, post-training, deployment and final commercialization. To our knowledge, this represents the first safety survey to encompass the entire lifecycle of LLMs. (II) Extensive Literature Support. Our research is grounded in an exhaustive review of over 800+ papers, ensuring comprehensive coverage and systematic organization of security issues within a more holistic understanding. (III) Unique Insights. Through systematic literature analysis, we have developed reliable roadmaps and perspectives for each chapter. Our work identifies promising research directions, including safety in data generation, alignment techniques, model editing, and LLM-based agent systems. These insights provide valuable guidance for researchers pursuing future work in this field.

Large Reasoning Models (LRMs) have exhibited extraordinary prowess in tasks like mathematics and coding, leveraging their advanced reasoning capabilities. Nevertheless, as these capabilities progress, significant concerns regarding their vulnerabilities and safety have arisen, which can pose challenges to their deployment and application in real-world settings. This paper presents a comprehensive survey of LRMs, meticulously exploring and summarizing the newly emerged safety risks, attacks, and defense strategies. By organizing these elements into a detailed taxonomy, this work aims to offer a clear and structured understanding of the current safety landscape of LRMs, facilitating future research and development to enhance the security and reliability of these powerful models.

Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms. While these agents hold great promise for advancing digital automation, their potential for unsafe operations, such as system compromise and privacy leakage, is raising significant concerns. Detecting these safety concerns across the vast and complex operational space of mobile environments presents a formidable challenge that remains critically underexplored. To establish a foundation for mobile agent safety research, we introduce MobileRisk-Live, a dynamic sandbox environment accompanied by a safety detection benchmark comprising realistic trajectories with fine-grained annotations. Built upon this, we propose OS-Sentinel, a novel hybrid safety detection framework that synergistically combines a Formal Verifier for detecting explicit system-level violations with a VLM-based Contextual Judge for assessing contextual risks and agent actions. Experiments show that OS-Sentinel achieves 10%-30% improvements over existing approaches across multiple metrics. Further analysis provides critical insights that foster the development of safer and more reliable autonomous mobile agents.

The increasing adoption of large language models (LLMs) in software engineering necessitates rigorous security evaluation of their generated code. However, existing benchmarks often lack relevance to real-world AI programming scenarios, making them inadequate for assessing the practical security risks associated with AI-generated code in production environments. To address this gap, we introduce A.S.E (AI Code Generation Security Evaluation), a repository-level evaluation benchmark designed to closely mirror real-world AI programming tasks, offering a comprehensive and reliable framework for assessing the security of AI-generated code. Our evaluation of leading LLMs on A.S.E reveals several key findings. In particular, current LLMs still struggle with secure coding. The complexity in repository-level scenarios presents challenges for LLMs that typically perform well on snippet-level tasks. Morever, a larger reasoning budget does not necessarily lead to better code generation. These observations offer valuable insights into the current state of AI code generation, assisting developers in selecting the most appropriate models for practical tasks, while laying the foundation for refining LLMs to generate secure and efficient code in real-world applications.

As large language models (LLMs) continue to advance in capability and influence, ensuring their security and preventing harmful outputs has become crucial. A promising approach to address these concerns involves training models to automatically generate adversarial prompts for red teaming. However, the evolving subtlety of vulnerabilities in LLMs challenges the effectiveness of current adversarial methods, which struggle to specifically target and explore the weaknesses of these models. To tackle these challenges, we introduce the Self-Evolving Adversarial Safety (SEAS) optimization framework, which enhances security by leveraging data generated by the model itself. SEAS operates through three iterative stages: Initialization, Attack, and Adversarial Optimization, refining both the Red Team and Target models to improve robustness and safety. This framework reduces reliance on manual testing and significantly enhances the security capabilities of LLMs. Our contributions include a novel adversarial framework, a comprehensive safety dataset, and after three iterations, the Target model achieves a security level comparable to GPT-4, while the Red Team model shows a marked increase in attack success rate (ASR) against advanced models.

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent's resilience on natural language inputs -- an especially dangerous threat when agents are granted tool access or handle sensitive information. In this work, we propose a set of principled design patterns for building AI agents with provable resistance to prompt injection. We systematically analyze these patterns, discuss their trade-offs in terms of utility and security, and illustrate their real-world applicability through a series of case studies.

The field of software security testing, more specifically penetration testing, is an activity that requires high levels of expertise and involves many manual testing and analysis steps. This paper explores the potential usage of large-language models, such as GPT3.5, to augment penetration testers with AI sparring partners. We explore the feasibility of supplementing penetration testers with AI models for two distinct use cases: high-level task planning for security testing assignments and low-level vulnerability hunting within a vulnerable virtual machine. For the latter, we implemented a closed-feedback loop between LLM-generated low-level actions with a vulnerable virtual machine (connected through SSH) and allowed the LLM to analyze the machine state for vulnerabilities and suggest concrete attack vectors which were automatically executed within the virtual machine. We discuss promising initial results, detail avenues for improvement, and close deliberating on the ethics of providing AI-based sparring partners.

Robotic Process Automation (RPA) systems face challenges in handling complex processes and diverse screen layouts that require advanced human-like decision-making capabilities. These systems typically rely on pixel-level encoding through drag-and-drop or automation frameworks such as Selenium to create navigation workflows, rather than visual understanding of screen elements. In this context, we present SmartFlow, an AI-based RPA system that uses pre-trained large language models (LLMs) coupled with deep-learning based image understanding. Our system can adapt to new scenarios, including changes in the user interface and variations in input data, without the need for human intervention. SmartFlow uses computer vision and natural language processing to perceive visible elements on the graphical user interface (GUI) and convert them into a textual representation. This information is then utilized by LLMs to generate a sequence of actions that are executed by a scripting engine to complete an assigned task. To assess the effectiveness of SmartFlow, we have developed a dataset that includes a set of generic enterprise applications with diverse layouts, which we are releasing for research use. Our evaluations on this dataset demonstrate that SmartFlow exhibits robustness across different layouts and applications. SmartFlow can automate a wide range of business processes such as form filling, customer service, invoice processing, and back-office operations. SmartFlow can thus assist organizations in enhancing productivity by automating an even larger fraction of screen-based workflows. The demo-video and dataset are available at https://smartflow-4c5a0a.webflow.io/.

The landscape of software development has witnessed a paradigm shift with the advent of AI-powered assistants, exemplified by GitHub Copilot. However, existing solutions are not leveraging all the potential capabilities available in an IDE such as building, testing, executing code, git operations, etc. Therefore, they are constrained by their limited capabilities, primarily focusing on suggesting code snippets and file manipulation within a chat-based interface. To fill this gap, we present AutoDev, a fully automated AI-driven software development framework, designed for autonomous planning and execution of intricate software engineering tasks. AutoDev enables users to define complex software engineering objectives, which are assigned to AutoDev's autonomous AI Agents to achieve. These AI agents can perform diverse operations on a codebase, including file editing, retrieval, build processes, execution, testing, and git operations. They also have access to files, compiler output, build and testing logs, static analysis tools, and more. This enables the AI Agents to execute tasks in a fully automated manner with a comprehensive understanding of the contextual information required. Furthermore, AutoDev establishes a secure development environment by confining all operations within Docker containers. This framework incorporates guardrails to ensure user privacy and file security, allowing users to define specific permitted or restricted commands and operations within AutoDev. In our evaluation, we tested AutoDev on the HumanEval dataset, obtaining promising results with 91.5% and 87.8% of Pass@1 for code generation and test generation respectively, demonstrating its effectiveness in automating software engineering tasks while maintaining a secure and user-controlled development environment.

As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees for AI agents. We present a formal model to reason about the security and expressiveness of agent planners. Using this model, we characterize the class of properties enforceable by dynamic taint-tracking and construct a taxonomy of tasks to evaluate security and utility trade-offs of planner designs. Informed by this exploration, we present Fides, a planner that tracks confidentiality and integrity labels, deterministically enforces security policies, and introduces novel primitives for selectively hiding information. Its evaluation in AgentDojo demonstrates that this approach broadens the range of tasks that can be securely accomplished. A tutorial to walk readers through the the concepts introduced in the paper can be found at https://github.com/microsoft/fides

We present a systematic security assessment of the Unitree G1 humanoid showing it operates simultaneously as a covert surveillance node and can be purposed as an active cyber operations platform. Initial access can be achieved by exploiting the BLE provisioning protocol which contains a critical command injection vulnerability allowing root access via malformed Wi-Fi credentials, exploitable using hardcoded AES keys shared across all units. Partial reverse engineering of Unitree's proprietary FMX encryption reveal a static Blowfish-ECB layer and a predictable LCG mask-enabled inspection of the system's otherwise sophisticated security architecture, the most mature we have observed in commercial robotics. Two empirical case studies expose the critical risk of this humanoid robot: (a) the robot functions as a trojan horse, continuously exfiltrating multi-modal sensor and service-state telemetry to 43.175.228.18:17883 and 43.175.229.18:17883 every 300 seconds without operator notice, creating violations of GDPR Articles 6 and 13; (b) a resident Cybersecurity AI (CAI) agent can pivot from reconnaissance to offensive preparation against any target, such as the manufacturer's cloud control plane, demonstrating escalation from passive monitoring to active counter-operations. These findings argue for adaptive CAI-powered defenses as humanoids move into critical infrastructure, contributing the empirical evidence needed to shape future security standards for physical-cyber convergence systems.

Intrusion detection system (IDS) is an important part of enterprise security system architecture. In particular, anomaly-based IDS has been widely applied to detect abnormal process behaviors that deviate from the majority. However, such abnormal behavior usually consists of a series of low-level heterogeneous events. The gap between the low-level events and the high-level abnormal behaviors makes it hard to infer which single events are related to the real abnormal activities, especially considering that there are massive "noisy" low-level events happening in between. Hence, the existing work that focus on detecting single entities/events can hardly achieve high detection accuracy. Different from previous work, we design and implement GID, an efficient graph-based intrusion detection technique that can identify abnormal event sequences from a massive heterogeneous process traces with high accuracy. GID first builds a compact graph structure to capture the interactions between different system entities. The suspiciousness or anomaly score of process paths is then measured by leveraging random walk technique to the constructed acyclic directed graph. To eliminate the score bias from the path length, the Box-Cox power transformation based approach is introduced to normalize the anomaly scores so that the scores of paths of different lengths have the same distribution. The efficiency of suspicious path discovery is further improved by the proposed optimization scheme. We fully implement our GID algorithm and deploy it into a real enterprise security system, and it greatly helps detect the advanced threats, and optimize the incident response. Executing GID on system monitoring datasets showing that GID is efficient (about 2 million records per minute) and accurate (higher than 80% in terms of detection rate).

Agents centered around Large Language Models (LLMs) are now capable of automating mobile device operations for users. After fine-tuning to learn a user's mobile operations, these agents can adhere to high-level user instructions online. They execute tasks such as goal decomposition, sequencing of sub-goals, and interactive environmental exploration, until the final objective is achieved. However, privacy concerns related to personalized user data arise during mobile operations, requiring user confirmation. Moreover, users' real-world operations are exploratory, with action data being complex and redundant, posing challenges for agent learning. To address these issues, in our practical application, we have designed interactive tasks between agents and humans to identify sensitive information and align with personalized user needs. Additionally, we integrated Standard Operating Procedure (SOP) information within the model's in-context learning to enhance the agent's comprehension of complex task execution. Our approach is evaluated on the new device control benchmark AitW, which encompasses 30K unique instructions across multi-step tasks, including application operation, web searching, and web shopping. Experimental results show that the SOP-based agent achieves state-of-the-art performance in LLMs without incurring additional inference costs, boasting an overall action success rate of 66.92\%. The code and data examples are available at https://github.com/alipay/mobile-agent.

We present the Process Engineering Operations Assistant (PEOA), an AI-driven framework designed to solve complex problems in the chemical and process industries. The framework employs a modular architecture orchestrated by a meta-agent, which serves as the central coordinator, managing an action generator and instruction-tuned small-scale language models (expert models). The action generator decomposes complex problems into sub-tasks and identifies suitable expert models to execute each, delivering precise solutions for multi-step problem-solving. Key techniques include advanced knowledge modeling using property graphs for improved information retrieval, facilitating more accurate and contextually relevant solutions. Additionally, the framework utilizes a teacher-student transfer-learning approach with GPT-4 (Omni) to fine-tune the action generator and expert models for domain adaptation, alongside an iterative problem-solving mechanism with sophisticated error handling. Custom datasets were developed to evaluate the framework against leading proprietary language models on various engineering tasks. The results demonstrate the framework effectiveness in automating calculations, accelerating prototyping, and providing AI-augmented decision support for industrial processes, marking a significant advancement in process engineering capabilities.

LLM agents are an emerging form of AI systems where large language models (LLMs) serve as the central component, utilizing a diverse set of tools to complete user-assigned tasks. Despite their great potential, LLM agents pose significant security risks. When interacting with the external world, they may encounter malicious commands from attackers, leading to the execution of dangerous actions. A promising way to address this is by enforcing the principle of least privilege: allowing only essential actions for task completion while blocking unnecessary ones. However, achieving this is challenging, as it requires covering diverse agent scenarios while preserving both security and utility. We introduce Progent, the first privilege control mechanism for LLM agents. At its core is a domain-specific language for flexibly expressing privilege control policies applied during agent execution. These policies provide fine-grained constraints over tool calls, deciding when tool calls are permissible and specifying fallbacks if they are not. This enables agent developers and users to craft suitable policies for their specific use cases and enforce them deterministically to guarantee security. Thanks to its modular design, integrating Progent does not alter agent internals and requires only minimal changes to agent implementation, enhancing its practicality and potential for widespread adoption. To automate policy writing, we leverage LLMs to generate policies based on user queries, which are then updated dynamically for improved security and utility. Our extensive evaluation shows that it enables strong security while preserving high utility across three distinct scenarios or benchmarks: AgentDojo, ASB, and AgentPoison. Furthermore, we perform an in-depth analysis, showcasing the effectiveness of its core components and the resilience of its automated policy generation against adaptive attacks.

We stress test monitoring systems for detecting covert misbehavior in autonomous LLM agents (e.g., secretly sharing private information). To this end, we systematize a monitor red teaming (MRT) workflow that incorporates: (1) varying levels of agent and monitor situational awareness; (2) distinct adversarial strategies to evade the monitor, such as prompt injection; and (3) two datasets and environments -- SHADE-Arena for tool-calling agents and our new CUA-SHADE-Arena, which extends TheAgentCompany, for computer-use agents. We run MRT on existing LLM monitor scaffoldings, which orchestrate LLMs and parse agent trajectories, alongside a new hybrid hierarchical-sequential scaffolding proposed in this work. Our empirical results yield three key findings. First, agent awareness dominates monitor awareness: an agent's knowledge that it is being monitored substantially degrades the monitor's reliability. On the contrary, providing the monitor with more information about the agent is less helpful than expected. Second, monitor scaffolding matters more than monitor awareness: the hybrid scaffolding consistently outperforms baseline monitor scaffolding, and can enable weaker models to reliably monitor stronger agents -- a weak-to-strong scaling effect. Third, in a human-in-the-loop setting where humans discuss with the LLM monitor to get an updated judgment for the agent's behavior, targeted human oversight is most effective; escalating only pre-flagged cases to human reviewers improved the TPR by approximately 15% at FPR = 0.01. Our work establishes a standard workflow for MRT, highlighting the lack of adversarial robustness for LLMs and humans when monitoring and detecting agent misbehavior. We release code, data, and logs to spur further research.

As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and multi-modal systems. Red-teaming has gained importance in proactively identifying weaknesses in these systems, while blue-teaming works to protect against such adversarial attacks. Despite growing academic interest in adversarial risks for generative AI, there is limited guidance tailored for practitioners to assess and mitigate these challenges in real-world environments. To address this, our contributions include: (1) a practical examination of red- and blue-teaming strategies for securing generative AI, (2) identification of key challenges and open questions in defense development and evaluation, and (3) the Attack Atlas, an intuitive framework that brings a practical approach to analyzing single-turn input attacks, placing it at the forefront for practitioners. This work aims to bridge the gap between academic insights and practical security measures for the protection of generative AI systems.

The increasing deployment of Large Language Models (LLMs) across enterprise and mission-critical domains has underscored the urgent need for robust guardrailing systems that ensure safety, reliability, and compliance. Existing solutions often struggle with real-time oversight, multi-modal data handling, and explainability -- limitations that hinder their adoption in regulated environments. Existing guardrails largely operate in isolation, focused on text alone making them inadequate for multi-modal, production-scale environments. We introduce Protect, natively multi-modal guardrailing model designed to operate seamlessly across text, image, and audio inputs, designed for enterprise-grade deployment. Protect integrates fine-tuned, category-specific adapters trained via Low-Rank Adaptation (LoRA) on an extensive, multi-modal dataset covering four safety dimensions: toxicity, sexism, data privacy, and prompt injection. Our teacher-assisted annotation pipeline leverages reasoning and explanation traces to generate high-fidelity, context-aware labels across modalities. Experimental results demonstrate state-of-the-art performance across all safety dimensions, surpassing existing open and proprietary models such as WildGuard, LlamaGuard-4, and GPT-4.1. Protect establishes a strong foundation for trustworthy, auditable, and production-ready safety systems capable of operating across text, image, and audio modalities.

As AI agents become integral to enterprise workflows, their reliance on shared tool libraries and pre-trained components creates significant supply chain vulnerabilities. While previous work has demonstrated behavioral backdoor detection within individual LLM architectures, the critical question of cross-LLM generalization remains unexplored, a gap with serious implications for organizations deploying multiple AI systems. We present the first systematic study of cross-LLM behavioral backdoor detection, evaluating generalization across six production LLMs (GPT-5.1, Claude Sonnet 4.5, Grok 4.1, Llama 4 Maverick, GPT-OSS 120B, and DeepSeek Chat V3.1). Through 1,198 execution traces and 36 cross-model experiments, we quantify a critical finding: single-model detectors achieve 92.7% accuracy within their training distribution but only 49.2% across different LLMs, a 43.4 percentage point generalization gap equivalent to random guessing. Our analysis reveals that this gap stems from model-specific behavioral signatures, particularly in temporal features (coefficient of variation > 0.8), while structural features remain stable across architectures. We show that model-aware detection incorporating model identity as an additional feature achieves 90.6% accuracy universally across all evaluated models. We release our multi-LLM trace dataset and detection framework to enable reproducible research.

AI agents are emerging as a dominant workload in a wide range of applications, promising to be the vehicle that delivers the promised benefits of AI to enterprises and consumers. Unlike conventional software or static inference, agentic workloads are dynamic and structurally complex. Often these agents are directed graphs of compute and IO operations that span multi-modal data input and conversion), data processing and context gathering (e.g vector DB lookups), multiple LLM inferences, tool calls, etc. To scale AI agent usage, we need efficient and scalable deployment and agent-serving infrastructure. To tackle this challenge, in this paper, we present a system design for dynamic orchestration of AI agent workloads on heterogeneous compute infrastructure spanning CPUs and accelerators, both from different vendors and across different performance tiers within a single vendor. The system delivers several building blocks: a framework for planning and optimizing agentic AI execution graphs using cost models that account for compute, memory, and bandwidth constraints of different HW; a MLIR based representation and compilation system that can decompose AI agent execution graphs into granular operators and generate code for different HW options; and a dynamic orchestration system that can place the granular components across a heterogeneous compute infrastructure and stitch them together while meeting an end-to-end SLA. Our design performs a systems level TCO optimization and preliminary results show that leveraging a heterogeneous infrastructure can deliver significant TCO benefits. A preliminary surprising finding is that for some workloads a heterogeneous combination of older generation GPUs with newer accelerators can deliver similar TCO as the latest generation homogenous GPU infrastructure design, potentially extending the life of deployed infrastructure.

The rapid shift from passive LLMs to autonomous LLM-agents marks a new paradigm in cybersecurity. While these agents can act as powerful tools for both offensive and defensive operations, the very agentic context introduces a new class of inherent security risks. In this work we present the first holistic survey of the agentic security landscape, structuring the field around three interdependent pillars: Applications, Threats, and Defenses. We provide a comprehensive taxonomy of over 150 papers, explaining how agents are used, the vulnerabilities they possess, and the countermeasures designed to protect them. A detailed cross-cutting analysis shows emerging trends in agent architecture while revealing critical research gaps in model and modality coverage.

This paper examines the evolution, architecture, and practical applications of AI agents from their early, rule-based incarnations to modern sophisticated systems that integrate large language models with dedicated modules for perception, planning, and tool use. Emphasizing both theoretical foundations and real-world deployments, the paper reviews key agent paradigms, discusses limitations of current evaluation benchmarks, and proposes a holistic evaluation framework that balances task effectiveness, efficiency, robustness, and safety. Applications across enterprise, personal assistance, and specialized domains are analyzed, with insights into future research directions for more resilient and adaptive AI agent systems.

Rising concern for the societal implications of artificial intelligence systems has inspired a wave of academic and journalistic literature in which deployed systems are audited for harm by investigators from outside the organizations deploying the algorithms. However, it remains challenging for practitioners to identify the harmful repercussions of their own systems prior to deployment, and, once deployed, emergent issues can become difficult or impossible to trace back to their source. In this paper, we introduce a framework for algorithmic auditing that supports artificial intelligence system development end-to-end, to be applied throughout the internal organization development lifecycle. Each stage of the audit yields a set of documents that together form an overall audit report, drawing on an organization's values or principles to assess the fit of decisions made throughout the process. The proposed auditing framework is intended to contribute to closing the accountability gap in the development and deployment of large-scale artificial intelligence systems by embedding a robust process to ensure audit integrity.

This survey examines the rapidly evolving field of Deep Research systems -- AI-powered applications that automate complex research workflows through the integration of large language models, advanced information retrieval, and autonomous reasoning capabilities. We analyze more than 80 commercial and non-commercial implementations that have emerged since 2023, including OpenAI/Deep Research, Gemini/Deep Research, Perplexity/Deep Research, and numerous open-source alternatives. Through comprehensive examination, we propose a novel hierarchical taxonomy that categorizes systems according to four fundamental technical dimensions: foundation models and reasoning engines, tool utilization and environmental interaction, task planning and execution control, and knowledge synthesis and output generation. We explore the architectural patterns, implementation approaches, and domain-specific adaptations that characterize these systems across academic, scientific, business, and educational applications. Our analysis reveals both the significant capabilities of current implementations and the technical and ethical challenges they present regarding information accuracy, privacy, intellectual property, and accessibility. The survey concludes by identifying promising research directions in advanced reasoning architectures, multimodal integration, domain specialization, human-AI collaboration, and ecosystem standardization that will likely shape the future evolution of this transformative technology. By providing a comprehensive framework for understanding Deep Research systems, this survey contributes to both the theoretical understanding of AI-augmented knowledge work and the practical development of more capable, responsible, and accessible research technologies. The paper resources can be viewed at https://github.com/scienceaix/deepresearch.

This study demonstrates a novel approach to testing the security boundaries of Vision-Large Language Model (VLM/ LLM) using the EICAR test file embedded within JPEG images. We successfully executed four distinct protocols across multiple LLM platforms, including OpenAI GPT-4o, Microsoft Copilot, Google Gemini 1.5 Pro, and Anthropic Claude 3.5 Sonnet. The experiments validated that a modified JPEG containing the EICAR signature could be uploaded, manipulated, and potentially executed within LLM virtual workspaces. Key findings include: 1) consistent ability to mask the EICAR string in image metadata without detection, 2) successful extraction of the test file using Python-based manipulation within LLM environments, and 3) demonstration of multiple obfuscation techniques including base64 encoding and string reversal. This research extends Microsoft Research's "Penetration Testing Rules of Engagement" framework to evaluate cloud-based generative AI and LLM security boundaries, particularly focusing on file handling and execution capabilities within containerized environments.

While reinforcement learning-trained Large Reasoning Models (LRMs, e.g., Deepseek-R1) demonstrate advanced reasoning capabilities in the evolving Large Language Models (LLMs) domain, their susceptibility to security threats remains a critical vulnerability. This weakness is particularly evident in Chain-of-Thought (CoT) generation processes, where adversarial methods like backdoor prompt attacks can systematically subvert the model's core reasoning mechanisms. The emerging Chain-of-Thought Attack (CoTA) reveals this vulnerability through exploiting prompt controllability, simultaneously degrading both CoT safety and task performance with low-cost interventions. To address this compounded security-performance vulnerability, we propose Thought Purity (TP): a defense paradigm that systematically strengthens resistance to malicious content while preserving operational efficacy. Our solution achieves this through three synergistic components: (1) a safety-optimized data processing pipeline (2) reinforcement learning-enhanced rule constraints (3) adaptive monitoring metrics. Our approach establishes the first comprehensive defense mechanism against CoTA vulnerabilities in reinforcement learning-aligned reasoning systems, significantly advancing the security-functionality equilibrium for next-generation AI architectures.

The emergence of agentic Artificial Intelligence (AI), which can operate autonomously, demonstrate goal-directed behavior, and adaptively learn, indicates the onset of a massive change in today's computing infrastructure. This study investigates how agentic AI models' multiple characteristics may impact the architecture, governance, and operation under which computing environments function. Agentic AI has the potential to reduce reliance on extremely large (public) cloud environments due to resource efficiency, especially with processing and/or storage. The aforementioned characteristics provide us with an opportunity to canvas the likelihood of strategic migration in computing infrastructures away from massive public cloud services, towards more locally distributed architectures: edge computing and on-premises computing infrastructures. Many of these likely migrations will be spurred by factors like on-premises processing needs, diminished data consumption footprints, and cost savings. This study examines how a solution for implementing AI's autonomy could result in a re-architecture of the systems and model a departure from today's governance models to help us manage these increasingly autonomous agents, and an operational overhaul of processes over a very diverse computing systems landscape that bring together computing via cloud, edge, and on-premises computing solutions. To enable us to explore these intertwined decisions, it will be fundamentally important to understand how to best position agentic AI, and to navigate the future state of computing infrastructures.

The integration of Large Language Models (LLMs) into software engineering has revolutionized code generation, enabling unprecedented productivity through promptware and autonomous AI agents. However, this transformation introduces significant risks, including insecure code generation, hallucinated outputs, irreversible actions, and a lack of transparency and accountability. Incidents like the Replit database deletion underscore the urgent need for robust safety and governance mechanisms. This paper comprehensively analyzes the inherent challenges of LLM-assisted code generation, such as vulnerability inheritance, overtrust, misinterpretation, and the absence of standardized validation and rollback protocols. To address these, we propose the SAFE-AI Framework, a holistic approach emphasizing Safety, Auditability, Feedback, and Explainability. The framework integrates guardrails, sandboxing, runtime verification, risk-aware logging, human-in-the-loop systems, and explainable AI techniques to mitigate risks while fostering trust and compliance. We introduce a novel taxonomy of AI behaviors categorizing suggestive, generative, autonomous, and destructive actions to guide risk assessment and oversight. Additionally, we identify open problems, including the lack of standardized benchmarks for code specific hallucinations and autonomy levels, and propose future research directions for hybrid verification, semantic guardrails, and proactive governance tools. Through detailed comparisons of autonomy control, prompt engineering, explainability, and governance frameworks, this paper provides a roadmap for responsible AI integration in software engineering, aligning with emerging regulations like the EU AI Act and Canada's AIDA to ensure safe, transparent, and accountable AI-driven development.

Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying them, including bias, potential for unsafe actions, dataset poisoning, lack of explainability, hallucinations, and non-reproducibility. These risks necessitate the development of "guardrails" to align LLMs with desired behaviors and mitigate potential harm. This work explores the risks associated with deploying LLMs and evaluates current approaches to implementing guardrails and model alignment techniques. We examine intrinsic and extrinsic bias evaluation methods and discuss the importance of fairness metrics for responsible AI development. The safety and reliability of agentic LLMs (those capable of real-world actions) are explored, emphasizing the need for testability, fail-safes, and situational awareness. Technical strategies for securing LLMs are presented, including a layered protection model operating at external, secondary, and internal levels. System prompts, Retrieval-Augmented Generation (RAG) architectures, and techniques to minimize bias and protect privacy are highlighted. Effective guardrail design requires a deep understanding of the LLM's intended use case, relevant regulations, and ethical considerations. Striking a balance between competing requirements, such as accuracy and privacy, remains an ongoing challenge. This work underscores the importance of continuous research and development to ensure the safe and responsible use of LLMs in real-world applications.

We introduce a finance & accounting benchmark (Finch) for evaluating AI agents on real-world, enterprise-grade professional workflows -- interleaving data entry, structuring, formatting, web search, cross-file retrieval, calculation, modeling, validation, translation, visualization, and reporting. Finch is sourced from authentic enterprise workspaces at Enron (15,000 spreadsheets and 500,000 emails from 150 employees) and other financial institutions, preserving in-the-wild messiness across multimodal artifacts (text, tables, formulas, charts, code, and images) and spanning diverse domains such as budgeting, trading, and asset management. We propose a workflow construction process that combines LLM-assisted discovery with expert annotation: (1) LLM-assisted, expert-verified derivation of workflows from real-world email threads and version histories of spreadsheet files, and (2) meticulous expert annotation for workflows, requiring over 700 hours of domain-expert effort. This yields 172 composite workflows with 384 tasks, involving 1,710 spreadsheets with 27 million cells, along with PDFs and other artifacts, capturing the intrinsically messy, long-horizon, knowledge-intensive, and collaborative nature of real-world enterprise work. We conduct both human and automated evaluations of frontier AI systems including GPT 5.1, Claude Sonnet 4.5, Gemini 3 Pro, Grok 4, and Qwen 3 Max, and GPT 5.1 Pro spends 48 hours in total yet passes only 38.4% of workflows, while Claude Sonnet 4.5 passes just 25.0%. Comprehensive case studies further surface the challenges that real-world enterprise workflows pose for AI agents.

Large Language Models (LLMs) are increasingly deployed in mission-critical systems, facilitating tasks such as satellite operations, command-and-control, military decision support, and cyber defense. Many of these systems are accessed through application programming interfaces (APIs). When such APIs lack robust access controls, they can expose full or top-k logits, creating a significant and often overlooked attack surface. Prior art has mainly focused on reconstructing the output projection layer or distilling surface-level behaviors. However, regenerating a black-box model under tight query constraints remains underexplored. We address that gap by introducing a constrained replication pipeline that transforms partial logit leakage into a functional deployable substitute model clone. Our two-stage approach (i) reconstructs the output projection matrix by collecting top-k logits from under 10k black-box queries via singular value decomposition (SVD) over the logits, then (ii) distills the remaining architecture into compact student models with varying transformer depths, trained on an open source dataset. A 6-layer student recreates 97.6% of the 6-layer teacher model's hidden-state geometry, with only a 7.31% perplexity increase, and a 7.58 Negative Log-Likelihood (NLL). A 4-layer variant achieves 17.1% faster inference and 18.1% parameter reduction with comparable performance. The entire attack completes in under 24 graphics processing unit (GPU) hours and avoids triggering API rate-limit defenses. These results demonstrate how quickly a cost-limited adversary can clone an LLM, underscoring the urgent need for hardened inference APIs and secure on-premise defense deployments.

The advent of large language models (LLMs) has catalyzed a transformative shift in artificial intelligence, paving the way for advanced intelligent agents capable of sophisticated reasoning, robust perception, and versatile action across diverse domains. As these agents increasingly drive AI research and practical applications, their design, evaluation, and continuous improvement present intricate, multifaceted challenges. This survey provides a comprehensive overview, framing intelligent agents within a modular, brain-inspired architecture that integrates principles from cognitive science, neuroscience, and computational research. We structure our exploration into four interconnected parts. First, we delve into the modular foundation of intelligent agents, systematically mapping their cognitive, perceptual, and operational modules onto analogous human brain functionalities, and elucidating core components such as memory, world modeling, reward processing, and emotion-like systems. Second, we discuss self-enhancement and adaptive evolution mechanisms, exploring how agents autonomously refine their capabilities, adapt to dynamic environments, and achieve continual learning through automated optimization paradigms, including emerging AutoML and LLM-driven optimization strategies. Third, we examine collaborative and evolutionary multi-agent systems, investigating the collective intelligence emerging from agent interactions, cooperation, and societal structures, highlighting parallels to human social dynamics. Finally, we address the critical imperative of building safe, secure, and beneficial AI systems, emphasizing intrinsic and extrinsic security threats, ethical alignment, robustness, and practical mitigation strategies necessary for trustworthy real-world deployment.

As information grows exponentially, enterprises face increasing pressure to transform unstructured data into coherent, actionable insights. While autonomous agents show promise, they often struggle with domain-specific nuances, intent alignment, and enterprise integration. We present Enterprise Deep Research (EDR), a multi-agent system that integrates (1) a Master Planning Agent for adaptive query decomposition, (2) four specialized search agents (General, Academic, GitHub, LinkedIn), (3) an extensible MCP-based tool ecosystem supporting NL2SQL, file analysis, and enterprise workflows, (4) a Visualization Agent for data-driven insights, and (5) a reflection mechanism that detects knowledge gaps and updates research direction with optional human-in-the-loop steering guidance. These components enable automated report generation, real-time streaming, and seamless enterprise deployment, as validated on internal datasets. On open-ended benchmarks including DeepResearch Bench and DeepConsult, EDR outperforms state-of-the-art agentic systems without any human steering. We release the EDR framework and benchmark trajectories to advance research on multi-agent reasoning applications. Code at https://github.com/SalesforceAIResearch/enterprise-deep-research and Dataset at https://huggingface.co/datasets/Salesforce/EDR-200

Recent advances in Large Language Models (LLMs) have spurred transformative applications in various domains, ranging from open-source to proprietary LLMs. However, jailbreak attacks, which aim to break safety alignment and user compliance by tricking the target LLMs into answering harmful and risky responses, are becoming an urgent concern. The practice of red-teaming for LLMs is to proactively explore potential risks and error-prone instances before the release of frontier AI technology. This paper proposes an agentic workflow to automate and scale the red-teaming process of LLMs through the Composition-of-Principles (CoP) framework, where human users provide a set of red-teaming principles as instructions to an AI agent to automatically orchestrate effective red-teaming strategies and generate jailbreak prompts. Distinct from existing red-teaming methods, our CoP framework provides a unified and extensible framework to encompass and orchestrate human-provided red-teaming principles to enable the automated discovery of new red-teaming strategies. When tested against leading LLMs, CoP reveals unprecedented safety risks by finding novel jailbreak prompts and improving the best-known single-turn attack success rate by up to 19.0 times.

Foundation models are increasingly becoming better autonomous programmers, raising the prospect that they could also automate dangerous offensive cyber-operations. Current frontier model audits probe the cybersecurity risks of such agents, but most fail to account for the degrees of freedom available to adversaries in the real world. In particular, with strong verifiers and financial incentives, agents for offensive cybersecurity are amenable to iterative improvement by would-be adversaries. We argue that assessments should take into account an expanded threat model in the context of cybersecurity, emphasizing the varying degrees of freedom that an adversary may possess in stateful and non-stateful environments within a fixed compute budget. We show that even with a relatively small compute budget (8 H100 GPU Hours in our study), adversaries can improve an agent's cybersecurity capability on InterCode CTF by more than 40\% relative to the baseline -- without any external assistance. These results highlight the need to evaluate agents' cybersecurity risk in a dynamic manner, painting a more representative picture of risk.

Recent advancements in Web AI agents have demonstrated remarkable capabilities in addressing complex web navigation tasks. However, emerging research shows that these agents exhibit greater vulnerability compared to standalone Large Language Models (LLMs), despite both being built upon the same safety-aligned models. This discrepancy is particularly concerning given the greater flexibility of Web AI Agent compared to standalone LLMs, which may expose them to a wider range of adversarial user inputs. To build a scaffold that addresses these concerns, this study investigates the underlying factors that contribute to the increased vulnerability of Web AI agents. Notably, this disparity stems from the multifaceted differences between Web AI agents and standalone LLMs, as well as the complex signals - nuances that simple evaluation metrics, such as success rate, often fail to capture. To tackle these challenges, we propose a component-level analysis and a more granular, systematic evaluation framework. Through this fine-grained investigation, we identify three critical factors that amplify the vulnerability of Web AI agents; (1) embedding user goals into the system prompt, (2) multi-step action generation, and (3) observational capabilities. Our findings highlights the pressing need to enhance security and robustness in AI agent design and provide actionable insights for targeted defense strategies.

Data-driven companies use AI models extensively to develop products and intelligent business solutions, making the health of these models crucial for business success. Model monitoring and alerting in industries pose unique challenges, including a lack of clear model health metrics definition, label sparsity, and fast model iterations that result in short-lived models and features. As a product, there are also requirements for scalability, generalizability, and explainability. To tackle these challenges, we propose AlerTiger, a deep-learning-based MLOps model monitoring system that helps AI teams across the company monitor their AI models' health by detecting anomalies in models' input features and output score over time. The system consists of four major steps: model statistics generation, deep-learning-based anomaly detection, anomaly post-processing, and user alerting. Our solution generates three categories of statistics to indicate AI model health, offers a two-stage deep anomaly detection solution to address label sparsity and attain the generalizability of monitoring new models, and provides holistic reports for actionable alerts. This approach has been deployed to most of LinkedIn's production AI models for over a year and has identified several model issues that later led to significant business metric gains after fixing.

Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use. Despite their growing capabilities, today's agent frameworks remain fragile, lacking principled mechanisms for secure information flow, reliability, and multi-agent coordination. In this work, we introduce SAFEFLOW, a new protocol-level framework for building trustworthy LLM/VLM-based agents. SAFEFLOW enforces fine-grained information flow control (IFC), precisely tracking provenance, integrity, and confidentiality of all the data exchanged between agents, tools, users, and environments. By constraining LLM reasoning to respect these security labels, SAFEFLOW prevents untrusted or adversarial inputs from contaminating high-integrity decisions. To ensure robustness in concurrent multi-agent settings, SAFEFLOW introduces transactional execution, conflict resolution, and secure scheduling over shared state, preserving global consistency across agents. We further introduce mechanisms, including write-ahead logging, rollback, and secure caches, that further enhance resilience against runtime errors and policy violations. To validate the performances, we built SAFEFLOWBENCH, a comprehensive benchmark suite designed to evaluate agent reliability under adversarial, noisy, and concurrent operational conditions. Extensive experiments demonstrate that agents built with SAFEFLOW maintain impressive task performance and security guarantees even in hostile environments, substantially outperforming state-of-the-art. Together, SAFEFLOW and SAFEFLOWBENCH lay the groundwork for principled, robust, and secure agent ecosystems, advancing the frontier of reliable autonomy.

Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms and impact on model integrity and confidentiality. Practical implementations, including adversarial examples, label flipping, and backdoor attacks, are explored alongside defenses such as adversarial training, differential privacy, and federated learning, highlighting their strengths and limitations. Advanced methods like contrastive and self-supervised learning are presented for enhancing robustness. The survey concludes with future directions, emphasizing automated defenses, zero-trust architectures, and the security challenges of large AI models. A balanced approach to performance and security is essential for developing reliable deep learning systems.

Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model can do - its capabilities - without assessing what it would do if endowed with high-risk capabilities. This leaves a critical blind spot: models may strategically conceal capabilities or rapidly acquire them, while harboring latent inclinations toward misuse. We argue that propensity - the likelihood of a model to pursue harmful actions if empowered - is a critical, yet underexplored, axis of safety evaluation. We present PropensityBench, a novel benchmark framework that assesses the proclivity of models to engage in risky behaviors when equipped with simulated dangerous capabilities using proxy tools. Our framework includes 5,874 scenarios with 6,648 tools spanning four high-risk domains: cybersecurity, self-proliferation, biosecurity, and chemical security. We simulate access to powerful capabilities via a controlled agentic environment and evaluate the models' choices under varying operational pressures that reflect real-world constraints or incentives models may encounter, such as resource scarcity or gaining more autonomy. Across open-source and proprietary frontier models, we uncover 9 alarming signs of propensity: models frequently choose high-risk tools when under pressure, despite lacking the capability to execute such actions unaided. These findings call for a shift from static capability audits toward dynamic propensity assessments as a prerequisite for deploying frontier AI systems safely. Our code is available at https://github.com/scaleapi/propensity-evaluation.

As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various settings in which a user may invoke an intelligent system. This paper proposes ASSERT, Automated Safety Scenario Red Teaming, consisting of three methods -- semantically aligned augmentation, target bootstrapping, and adversarial knowledge injection. For robust safety evaluation, we apply these methods in the critical domain of AI safety to algorithmically generate a test suite of prompts covering diverse robustness settings -- semantic equivalence, related scenarios, and adversarial. We partition our prompts into four safety domains for a fine-grained analysis of how the domain affects model performance. Despite dedicated safeguards in existing state-of-the-art models, we find statistically significant performance differences of up to 11% in absolute classification accuracy among semantically related scenarios and error rates of up to 19% absolute error in zero-shot adversarial settings, raising concerns for users' physical safety.

As AI technology advances, it is driving innovation across industries, increasing the demand for scalable AI project deployment. However, deployment remains a critical challenge due to complex environment configurations, dependency conflicts, cross-platform adaptation, and debugging difficulties, which hinder automation and adoption. This paper introduces AI2Agent, an end-to-end framework that automates AI project deployment through guideline-driven execution, self-adaptive debugging, and case \& solution accumulation. AI2Agent dynamically analyzes deployment challenges, learns from past cases, and iteratively refines its approach, significantly reducing human intervention. To evaluate its effectiveness, we conducted experiments on 30 AI deployment cases, covering TTS, text-to-image generation, image editing, and other AI applications. Results show that AI2Agent significantly reduces deployment time and improves success rates. The code and demo video are now publicly accessible.

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted triggers and static data pipelines, which are rigid, labor-intensive, and inadequate for systematically evaluating modern defense robustness. As AI agents become increasingly capable, there is a growing need for more rigorous, diverse, and scalable red-teaming frameworks that can realistically simulate backdoor threats and assess model resilience under adversarial conditions. In this work, we introduce AutoBackdoor, a general framework for automating backdoor injection, encompassing trigger generation, poisoned data construction, and model fine-tuning via an autonomous agent-driven pipeline. Unlike prior approaches, AutoBackdoor uses a powerful language model agent to generate semantically coherent, context-aware trigger phrases, enabling scalable poisoning across arbitrary topics with minimal human effort. We evaluate AutoBackdoor under three realistic threat scenarios, including Bias Recommendation, Hallucination Injection, and Peer Review Manipulation, to simulate a broad range of attacks. Experiments on both open-source and commercial models, including LLaMA-3, Mistral, Qwen, and GPT-4o, demonstrate that our method achieves over 90\% attack success with only a small number of poisoned samples. More importantly, we find that existing defenses often fail to mitigate these attacks, underscoring the need for more rigorous and adaptive evaluation techniques against agent-driven threats as explored in this work. All code, datasets, and experimental configurations will be merged into our primary repository at https://github.com/bboylyg/BackdoorLLM.

We propose a framework for classifying the capabilities and behavior of Artificial General Intelligence (AGI) models and their precursors. This framework introduces levels of AGI performance, generality, and autonomy, providing a common language to compare models, assess risks, and measure progress along the path to AGI. To develop our framework, we analyze existing definitions of AGI, and distill six principles that a useful ontology for AGI should satisfy. With these principles in mind, we propose "Levels of AGI" based on depth (performance) and breadth (generality) of capabilities, and reflect on how current systems fit into this ontology. We discuss the challenging requirements for future benchmarks that quantify the behavior and capabilities of AGI models against these levels. Finally, we discuss how these levels of AGI interact with deployment considerations such as autonomy and risk, and emphasize the importance of carefully selecting Human-AI Interaction paradigms for responsible and safe deployment of highly capable AI systems.

As Large Language Models (LLMs) are deployed and integrated into thousands of applications, the need for scalable evaluation of how models respond to adversarial attacks grows rapidly. However, LLM security is a moving target: models produce unpredictable output, are constantly updated, and the potential adversary is highly diverse: anyone with access to the internet and a decent command of natural language. Further, what constitutes a security weak in one context may not be an issue in a different context; one-fits-all guardrails remain theoretical. In this paper, we argue that it is time to rethink what constitutes ``LLM security'', and pursue a holistic approach to LLM security evaluation, where exploration and discovery of issues are central. To this end, this paper introduces garak (Generative AI Red-teaming and Assessment Kit), a framework which can be used to discover and identify vulnerabilities in a target LLM or dialog system. garak probes an LLM in a structured fashion to discover potential vulnerabilities. The outputs of the framework describe a target model's weaknesses, contribute to an informed discussion of what composes vulnerabilities in unique contexts, and can inform alignment and policy discussions for LLM deployment.

This paper identifies and analyzes a novel vulnerability class in Model Context Protocol (MCP) based agent systems. The attack chain describes and demonstrates how benign, individually authorized tasks can be orchestrated to produce harmful emergent behaviors. Through systematic analysis using the MITRE ATLAS framework, we demonstrate how 95 agents tested with access to multiple services-including browser automation, financial analysis, location tracking, and code deployment-can chain legitimate operations into sophisticated attack sequences that extend beyond the security boundaries of any individual service. These red team exercises survey whether current MCP architectures lack cross-domain security measures necessary to detect or prevent a large category of compositional attacks. We present empirical evidence of specific attack chains that achieve targeted harm through service orchestration, including data exfiltration, financial manipulation, and infrastructure compromise. These findings reveal that the fundamental security assumption of service isolation fails when agents can coordinate actions across multiple domains, creating an exponential attack surface that grows with each additional capability. This research provides a barebones experimental framework that evaluate not whether agents can complete MCP benchmark tasks, but what happens when they complete them too well and optimize across multiple services in ways that violate human expectations and safety constraints. We propose three concrete experimental directions using the existing MCP benchmark suite.

The autonomous AI agents using large language models can create undeniable values in all span of the society but they face security threats from adversaries that warrants immediate protective solutions because trust and safety issues arise. Considering the many-shot jailbreaking and deceptive alignment as some of the main advanced attacks, that cannot be mitigated by the static guardrails used during the supervised training, points out a crucial research priority for real world robustness. The combination of static guardrails in dynamic multi-agent system fails to defend against those attacks. We intend to enhance security for LLM-based agents through the development of new evaluation frameworks which identify and counter threats for safe operational deployment. Our work uses three examination methods to detect rogue agents through a Reverse Turing Test and analyze deceptive alignment through multi-agent simulations and develops an anti-jailbreaking system by testing it with GEMINI 1.5 pro and llama-3.3-70B, deepseek r1 models using tool-mediated adversarial scenarios. The detection capabilities are strong such as 94\% accuracy for GEMINI 1.5 pro yet the system suffers persistent vulnerabilities when under long attacks as prompt length increases attack success rates (ASR) and diversity metrics become ineffective in prediction while revealing multiple complex system faults. The findings demonstrate the necessity of adopting flexible security systems based on active monitoring that can be performed by the agents themselves together with adaptable interventions by system admin as the current models can create vulnerabilities that can lead to the unreliable and vulnerable system. So, in our work, we try to address such situations and propose a comprehensive framework to counteract the security issues.

AI for Industrial Asset Lifecycle Management aims to automate complex operational workflows -- such as condition monitoring, maintenance planning, and intervention scheduling -- to reduce human workload and minimize system downtime. Traditional AI/ML approaches have primarily tackled these problems in isolation, solving narrow tasks within the broader operational pipeline. In contrast, the emergence of AI agents and large language models (LLMs) introduces a next-generation opportunity: enabling end-to-end automation across the entire asset lifecycle. This paper envisions a future where AI agents autonomously manage tasks that previously required distinct expertise and manual coordination. To this end, we introduce AssetOpsBench -- a unified framework and environment designed to guide the development, orchestration, and evaluation of domain-specific agents tailored for Industry 4.0 applications. We outline the key requirements for such holistic systems and provide actionable insights into building agents that integrate perception, reasoning, and control for real-world industrial operations. The software is available at https://github.com/IBM/AssetOpsBench.

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which rely on post hoc output filtering, are often brittle and fail to address the root cause: the model's inability to distinguish trusted instructions from untrusted data. This paper proposes Countermind, a multi-layered security architecture intended to shift defenses from a reactive, post hoc posture to a proactive, pre-inference, and intra-inference enforcement model. The architecture proposes a fortified perimeter designed to structurally validate and transform all inputs, and an internal governance mechanism intended to constrain the model's semantic processing pathways before an output is generated. The primary contributions of this work are conceptual designs for: (1) A Semantic Boundary Logic (SBL) with a mandatory, time-coupled Text Crypter intended to reduce the plaintext prompt injection attack surface, provided all ingestion paths are enforced. (2) A Parameter-Space Restriction (PSR) mechanism, leveraging principles from representation engineering, to dynamically control the LLM's access to internal semantic clusters, with the goal of mitigating semantic drift and dangerous emergent behaviors. (3) A Secure, Self-Regulating Core that uses an OODA loop and a learning security module to adapt its defenses based on an immutable audit log. (4) A Multimodal Input Sandbox and Context-Defense mechanisms to address threats from non-textual data and long-term semantic poisoning. This paper outlines an evaluation plan designed to quantify the proposed architecture's effectiveness in reducing the Attack Success Rate (ASR) for form-first attacks and to measure its potential latency overhead.

One major goal of the AI security community is to securely and reliably produce and deploy deep learning models for real-world applications. To this end, data poisoning based backdoor attacks on deep neural networks (DNNs) in the production stage (or training stage) and corresponding defenses are extensively explored in recent years. Ironically, backdoor attacks in the deployment stage, which can often happen in unprofessional users' devices and are thus arguably far more threatening in real-world scenarios, draw much less attention of the community. We attribute this imbalance of vigilance to the weak practicality of existing deployment-stage backdoor attack algorithms and the insufficiency of real-world attack demonstrations. To fill the blank, in this work, we study the realistic threat of deployment-stage backdoor attacks on DNNs. We base our study on a commonly used deployment-stage attack paradigm -- adversarial weight attack, where adversaries selectively modify model weights to embed backdoor into deployed DNNs. To approach realistic practicality, we propose the first gray-box and physically realizable weights attack algorithm for backdoor injection, namely subnet replacement attack (SRA), which only requires architecture information of the victim model and can support physical triggers in the real world. Extensive experimental simulations and system-level real-world attack demonstrations are conducted. Our results not only suggest the effectiveness and practicality of the proposed attack algorithm, but also reveal the practical risk of a novel type of computer virus that may widely spread and stealthily inject backdoor into DNN models in user devices. By our study, we call for more attention to the vulnerability of DNNs in the deployment stage.

As large language models (LLMs) become increasingly capable, security and safety evaluation are crucial. While current red teaming approaches have made strides in assessing LLM vulnerabilities, they often rely heavily on human input and lack comprehensive coverage of emerging attack vectors. This paper introduces AutoRedTeamer, a novel framework for fully automated, end-to-end red teaming against LLMs. AutoRedTeamer combines a multi-agent architecture with a memory-guided attack selection mechanism to enable continuous discovery and integration of new attack vectors. The dual-agent framework consists of a red teaming agent that can operate from high-level risk categories alone to generate and execute test cases and a strategy proposer agent that autonomously discovers and implements new attacks by analyzing recent research. This modular design allows AutoRedTeamer to adapt to emerging threats while maintaining strong performance on existing attack vectors. We demonstrate AutoRedTeamer's effectiveness across diverse evaluation settings, achieving 20% higher attack success rates on HarmBench against Llama-3.1-70B while reducing computational costs by 46% compared to existing approaches. AutoRedTeamer also matches the diversity of human-curated benchmarks in generating test cases, providing a comprehensive, scalable, and continuously evolving framework for evaluating the security of AI systems.

In this position paper, we address the persistent gap between rapidly growing AI capabilities and lagging safety progress. Existing paradigms divide into ``Make AI Safe'', which applies post-hoc alignment and guardrails but remains brittle and reactive, and ``Make Safe AI'', which emphasizes intrinsic safety but struggles to address unforeseen risks in open-ended environments. We therefore propose safe-by-coevolution as a new formulation of the ``Make Safe AI'' paradigm, inspired by biological immunity, in which safety becomes a dynamic, adversarial, and ongoing learning process. To operationalize this vision, we introduce R^2AI -- Resistant and Resilient AI -- as a practical framework that unites resistance against known threats with resilience to unforeseen risks. R^2AI integrates fast and slow safe models, adversarial simulation and verification through a safety wind tunnel, and continual feedback loops that guide safety and capability to coevolve. We argue that this framework offers a scalable and proactive path to maintain continual safety in dynamic environments, addressing both near-term vulnerabilities and long-term existential risks as AI advances toward AGI and ASI.

The rapid advancement of Large Language Models (LLMs) has opened up new opportunities for leveraging artificial intelligence in various domains, including cybersecurity. As the volume and sophistication of cyber threats continue to grow, there is an increasing need for intelligent systems that can automatically detect vulnerabilities, analyze malware, and respond to attacks. In this survey, we conduct a comprehensive review of the literature on the application of LLMs in cybersecurity (LLM4Security). By comprehensively collecting over 30K relevant papers and systematically analyzing 127 papers from top security and software engineering venues, we aim to provide a holistic view of how LLMs are being used to solve diverse problems across the cybersecurity domain. Through our analysis, we identify several key findings. First, we observe that LLMs are being applied to a wide range of cybersecurity tasks, including vulnerability detection, malware analysis, network intrusion detection, and phishing detection. Second, we find that the datasets used for training and evaluating LLMs in these tasks are often limited in size and diversity, highlighting the need for more comprehensive and representative datasets. Third, we identify several promising techniques for adapting LLMs to specific cybersecurity domains, such as fine-tuning, transfer learning, and domain-specific pre-training. Finally, we discuss the main challenges and opportunities for future research in LLM4Security, including the need for more interpretable and explainable models, the importance of addressing data privacy and security concerns, and the potential for leveraging LLMs for proactive defense and threat hunting. Overall, our survey provides a comprehensive overview of the current state-of-the-art in LLM4Security and identifies several promising directions for future research.

The Internet of Things has expanded rapidly, transforming communication and operations across industries but also increasing the attack surface and security breaches. Artificial Intelligence plays a key role in securing IoT, enabling attack detection, attack behavior analysis, and mitigation suggestion. Despite advancements, evaluations remain purely qualitative, and the lack of a standardized, objective benchmark for quantitatively measuring AI-based attack analysis and mitigation hinders consistent assessment of model effectiveness. In this work, we propose a hybrid framework combining Machine Learning (ML) for multi-class attack detection with Large Language Models (LLMs) for attack behavior analysis and mitigation suggestion. After benchmarking several ML and Deep Learning (DL) classifiers on the Edge-IIoTset and CICIoT2023 datasets, we applied structured role-play prompt engineering with Retrieval-Augmented Generation (RAG) to guide ChatGPT-o3 and DeepSeek-R1 in producing detailed, context-aware responses. We introduce novel evaluation metrics for quantitative assessment to guide us and an ensemble of judge LLMs, namely ChatGPT-4o, DeepSeek-V3, Mixtral 8x7B Instruct, Gemini 2.5 Flash, Meta Llama 4, TII Falcon H1 34B Instruct, xAI Grok 3, and Claude 4 Sonnet, to independently evaluate the responses. Results show that Random Forest has the best detection model, and ChatGPT-o3 outperformed DeepSeek-R1 in attack analysis and mitigation.

This paper presents our ongoing work toward developing an enterprise-ready Computer Using Generalist Agent (CUGA) system. Our research highlights the evolutionary nature of building agentic systems suitable for enterprise environments. By integrating state-of-the-art agentic AI techniques with a systematic approach to iterative evaluation, analysis, and refinement, we have achieved rapid and cost-effective performance gains, notably reaching a new state-of-the-art performance on the WebArena benchmark. We detail our development roadmap, the methodology and tools that facilitated rapid learning from failures and continuous system refinement, and discuss key lessons learned and future challenges for enterprise adoption.

Organizations are increasingly targeted by Advanced Persistent Threats (APTs), which involve complex, multi-stage tactics and diverse techniques. Cyber Threat Intelligence (CTI) sources, such as incident reports and security blogs, provide valuable insights, but are often unstructured and in natural language, making it difficult to automatically extract information. Recent studies have explored the use of AI to perform automatic extraction from CTI data, leveraging existing CTI datasets for performance evaluation and fine-tuning. However, they present challenges and limitations that impact their effectiveness. To overcome these issues, we introduce a novel dataset manually constructed from CTI reports and structured according to the MITRE ATT&CK framework. To assess its quality, we conducted an inter-annotator agreement study using Krippendorff alpha, confirming its reliability. Furthermore, the dataset was used to evaluate a Large Language Model (LLM) in a real-world business context, showing promising generalizability.

The rapid advancement of artificial intelligence (AI) has significantly expanded the attack surface for AI-driven cybersecurity threats, necessitating adaptive defense strategies. This paper introduces CyberSentinel, a unified, single-agent system for emergent threat detection, designed to identify and mitigate novel security risks in real time. CyberSentinel integrates: (1) Brute-force attack detection through SSH log analysis, (2) Phishing threat assessment using domain blacklists and heuristic URL scoring, and (3) Emergent threat detection via machine learning-based anomaly detection. By continuously adapting to evolving adversarial tactics, CyberSentinel strengthens proactive cybersecurity defense, addressing critical vulnerabilities in AI security.

Recent advances in large language models (LLMs) have made them indispensable, raising significant concerns over managing their safety. Automated red teaming offers a promising alternative to the labor-intensive and error-prone manual probing for vulnerabilities, providing more consistent and scalable safety evaluations. However, existing approaches often compromise diversity by focusing on maximizing attack success rate. Additionally, methods that decrease the cosine similarity from historical embeddings with semantic diversity rewards lead to novelty stagnation as history grows. To address these issues, we introduce DiveR-CT, which relaxes conventional constraints on the objective and semantic reward, granting greater freedom for the policy to enhance diversity. Our experiments demonstrate DiveR-CT's marked superiority over baselines by 1) generating data that perform better in various diversity metrics across different attack success rate levels, 2) better-enhancing resiliency in blue team models through safety tuning based on collected data, 3) allowing dynamic control of objective weights for reliable and controllable attack success rates, and 4) reducing susceptibility to reward overoptimization. Project details and code can be found at https://andrewzh112.github.io/#diverct.

Ensuring safe and effective use of AI requires understanding and anticipating its performance on novel tasks, from advanced scientific challenges to transformed workplace activities. So far, benchmarking has guided progress in AI, but it has offered limited explanatory and predictive power for general-purpose AI systems, given the low transferability across diverse tasks. In this paper, we introduce general scales for AI evaluation that can explain what common AI benchmarks really measure, extract ability profiles of AI systems, and predict their performance for new task instances, in- and out-of-distribution. Our fully-automated methodology builds on 18 newly-crafted rubrics that place instance demands on general scales that do not saturate. Illustrated for 15 large language models and 63 tasks, high explanatory power is unleashed from inspecting the demand and ability profiles, bringing insights on the sensitivity and specificity exhibited by different benchmarks, and how knowledge, metacognition and reasoning are affected by model size, chain-of-thought and distillation. Surprisingly, high predictive power at the instance level becomes possible using these demand levels, providing superior estimates over black-box baseline predictors based on embeddings or finetuning, especially in out-of-distribution settings (new tasks and new benchmarks). The scales, rubrics, battery, techniques and results presented here represent a major step for AI evaluation, underpinning the reliable deployment of AI in the years ahead. (Collaborative platform: https://kinds-of-intelligence-cfi.github.io/ADELE.)

In this report we describe the development of Command A, a powerful large language model purpose-built to excel at real-world enterprise use cases. Command A is an agent-optimised and multilingual-capable model, with support for 23 languages of global business, and a novel hybrid architecture balancing efficiency with top of the range performance. It offers best-in-class Retrieval Augmented Generation (RAG) capabilities with grounding and tool use to automate sophisticated business processes. These abilities are achieved through a decentralised training approach, including self-refinement algorithms and model merging techniques. We also include results for Command R7B which shares capability and architectural similarities to Command A. Weights for both models have been released for research purposes. This technical report details our original training pipeline and presents an extensive evaluation of our models across a suite of enterprise-relevant tasks and public benchmarks, demonstrating excellent performance and efficiency.

Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection. Current evaluations of this threat either lack support realistic but controlled environments or ignore hybrid web-OS attack scenarios involving both interfaces. To address this, we propose RedTeamCUA, an adversarial testing framework featuring a novel hybrid sandbox that integrates a VM-based OS environment with Docker-based web platforms. Our sandbox supports key features tailored for red teaming, such as flexible adversarial scenario configuration, and a setting that decouples adversarial evaluation from navigational limitations of CUAs by initializing tests directly at the point of an adversarial injection. Using RedTeamCUA, we develop RTC-Bench, a comprehensive benchmark with 864 examples that investigate realistic, hybrid web-OS attack scenarios and fundamental security vulnerabilities. Benchmarking current frontier CUAs identifies significant vulnerabilities: Claude 3.7 Sonnet | CUA demonstrates an ASR of 42.9%, while Operator, the most secure CUA evaluated, still exhibits an ASR of 7.6%. Notably, CUAs often attempt to execute adversarial tasks with an Attempt Rate as high as 92.5%, although failing to complete them due to capability limitations. Nevertheless, we observe concerning ASRs of up to 50% in realistic end-to-end settings, with the recently released frontier Claude 4 Opus | CUA showing an alarming ASR of 48%, demonstrating that indirect prompt injection presents tangible risks for even advanced CUAs despite their capabilities and safeguards. Overall, RedTeamCUA provides an essential framework for advancing realistic, controlled, and systematic analysis of CUA vulnerabilities, highlighting the urgent need for robust defenses to indirect prompt injection prior to real-world deployment.

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly complete harmful side tasks, such as backdoor insertion. In practice, most AI control protocols are fundamentally based on LLM monitors, which can become a central point of failure. We study adaptive attacks by an untrusted model that knows the protocol and the monitor model, which is plausible if the untrusted model was trained with a later knowledge cutoff or can search for this information autonomously. We instantiate a simple adaptive attack vector by which the attacker embeds publicly known or zero-shot prompt injections in the model outputs. Using this tactic, frontier models consistently evade diverse monitors and complete malicious tasks on two main AI control benchmarks. The attack works universally against current protocols that rely on a monitor. Furthermore, the recent Defer-to-Resample protocol even backfires, as its resampling amplifies the prompt injection and effectively reframes it as a best-of-n attack. In general, adaptive attacks on monitor models represent a major blind spot in current control protocols and should become a standard component of evaluations for future AI control mechanisms.

In the dynamic landscape of Industry 4.0, achieving efficiency, precision, and adaptability is essential to optimize manufacturing operations. Industries suffer due to supply chain disruptions caused by anomalies, which are being detected by current AI models but leaving domain experts uncertain without deeper insights into these anomalies. Additionally, operational inefficiencies persist due to inaccurate production forecasts and the limited effectiveness of traditional AI models for processing complex sensor data. Despite these advancements, existing systems lack the seamless integration of these capabilities needed to create a truly unified solution for enhancing production and decision-making. We propose SmartPilot, a neurosymbolic, multiagent CoPilot designed for advanced reasoning and contextual decision-making to address these challenges. SmartPilot processes multimodal sensor data and is compact to deploy on edge devices. It focuses on three key tasks: anomaly prediction, production forecasting, and domain-specific question answering. By bridging the gap between AI capabilities and real-world industrial needs, SmartPilot empowers industries with intelligent decision-making and drives transformative innovation in manufacturing. The demonstration video, datasets, and supplementary materials are available at https://github.com/ChathurangiShyalika/SmartPilot.

Despite significant advancements in general-purpose AI agents, several challenges still hinder their practical application in real-world scenarios. First, the limited planning capabilities of Large Language Models (LLM) restrict AI agents from effectively solving complex tasks that require long-horizon planning. Second, general-purpose AI agents struggle to efficiently utilize domain-specific knowledge and human expertise. In this paper, we introduce the Standard Operational Procedure-guided Agent (SOP-agent), a novel framework for constructing domain-specific agents through pseudocode-style Standard Operational Procedures (SOPs) written in natural language. Formally, we represent a SOP as a decision graph, which is traversed to guide the agent in completing tasks specified by the SOP. We conduct extensive experiments across tasks in multiple domains, including decision-making, search and reasoning, code generation, data cleaning, and grounded customer service. The SOP-agent demonstrates excellent versatility, achieving performance superior to general-purpose agent frameworks and comparable to domain-specific agent systems. Additionally, we introduce the Grounded Customer Service Benchmark, the first benchmark designed to evaluate the grounded decision-making capabilities of AI agents in customer service scenarios based on SOPs.

The living-off-the-land (LOTL) offensive methodologies rely on the perpetration of malicious actions through chains of commands executed by legitimate applications, identifiable exclusively by analysis of system logs. LOTL techniques are well hidden inside the stream of events generated by common legitimate activities, moreover threat actors often camouflage activity through obfuscation, making them particularly difficult to detect without incurring in plenty of false alarms, even using machine learning. To improve the performance of models in such an harsh environment, we propose an augmentation framework to enhance and diversify the presence of LOTL malicious activity inside legitimate logs. Guided by threat intelligence, we generate a dataset by injecting attack templates known to be employed in the wild, further enriched by malleable patterns of legitimate activities to replicate the behavior of evasive threat actors. We conduct an extensive ablation study to understand which models better handle our augmented dataset, also manipulated to mimic the presence of model-agnostic evasion and poisoning attacks. Our results suggest that augmentation is needed to maintain high-predictive capabilities, robustness to attack is achieved through specific hardening techniques like adversarial training, and it is possible to deploy near-real-time models with almost-zero false alarms.

Large Language Models (LLMs) for code generation (i.e., Code LLMs) have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studies have shown that these models are prone to generating vulnerable or even malicious code under adversarial settings. Existing red-teaming approaches rely on extensive human effort, limiting their scalability and practicality, and generally overlook the interactive nature of real-world AI-assisted programming, which often unfolds over multiple turns. To bridge these gaps, we present RedCoder, a red-teaming agent that engages victim models in multi-turn conversation to elicit vulnerable code. The pipeline to construct RedCoder begins with a multi-agent gaming process that simulates adversarial interactions, yielding a set of prototype conversations and an arsenal of reusable attack strategies. We then fine-tune an LLM on these prototype conversations to serve as the backbone of RedCoder. Once deployed, RedCoder autonomously engages Code LLMs in multi-turn conversations, dynamically retrieving relevant strategies from the arsenal to steer the dialogue toward vulnerability-inducing outputs. Experiments across multiple Code LLMs show that our approach outperforms prior single-turn and multi-turn red-team methods in inducing vulnerabilities in code generation, offering a scalable and effective tool for evaluating the security boundaries of modern code-generation systems.

As large language models (LLMs) become increasingly integrated into real-world applications, safeguarding them against unsafe, malicious, or privacy-violating content is critically important. We present OpenGuardrails, the first open-source project to provide both a context-aware safety and manipulation detection model and a deployable platform for comprehensive AI guardrails. OpenGuardrails protects against content-safety risks, model-manipulation attacks (e.g., prompt injection, jailbreaking, code-interpreter abuse, and the generation/execution of malicious code), and data leakage. Content-safety and model-manipulation detection are implemented by a unified large model, while data-leakage identification and redaction are performed by a separate lightweight NER pipeline (e.g., Presidio-style models or regex-based detectors). The system can be deployed as a security gateway or an API-based service, with enterprise-grade, fully private deployment options. OpenGuardrails achieves state-of-the-art (SOTA) performance on safety benchmarks, excelling in both prompt and response classification across English, Chinese, and multilingual tasks. All models are released under the Apache 2.0 license for public use.

As AI models are increasingly deployed across diverse real-world scenarios, ensuring their safety remains a critical yet underexplored challenge. While substantial efforts have been made to evaluate and enhance AI safety, the lack of a standardized framework and comprehensive toolkit poses significant obstacles to systematic research and practical adoption. To bridge this gap, we introduce AISafetyLab, a unified framework and toolkit that integrates representative attack, defense, and evaluation methodologies for AI safety. AISafetyLab features an intuitive interface that enables developers to seamlessly apply various techniques while maintaining a well-structured and extensible codebase for future advancements. Additionally, we conduct empirical studies on Vicuna, analyzing different attack and defense strategies to provide valuable insights into their comparative effectiveness. To facilitate ongoing research and development in AI safety, AISafetyLab is publicly available at https://github.com/thu-coai/AISafetyLab, and we are committed to its continuous maintenance and improvement.

While Large Language Models have shown promise in cybersecurity applications, their effectiveness in identifying security threats within cloud deployments remains unexplored. This paper introduces AWS Cloud Security Engineering Eval, a novel dataset for evaluating LLMs cloud security threat modeling capabilities. ACSE-Eval contains 100 production grade AWS deployment scenarios, each featuring detailed architectural specifications, Infrastructure as Code implementations, documented security vulnerabilities, and associated threat modeling parameters. Our dataset enables systemic assessment of LLMs abilities to identify security risks, analyze attack vectors, and propose mitigation strategies in cloud environments. Our evaluations on ACSE-Eval demonstrate that GPT 4.1 and Gemini 2.5 Pro excel at threat identification, with Gemini 2.5 Pro performing optimally in 0-shot scenarios and GPT 4.1 showing superior results in few-shot settings. While GPT 4.1 maintains a slight overall performance advantage, Claude 3.7 Sonnet generates the most semantically sophisticated threat models but struggles with threat categorization and generalization. To promote reproducibility and advance research in automated cybersecurity threat analysis, we open-source our dataset, evaluation metrics, and methodologies.

The deployment of agent systems in an enterprise environment is often hindered by several challenges: common models lack domain-specific process knowledge, leading to disorganized plans, missing key tools, and poor execution stability. To address this, this paper introduces Routine, a multi-step agent planning framework designed with a clear structure, explicit instructions, and seamless parameter passing to guide the agent's execution module in performing multi-step tool-calling tasks with high stability. In evaluations conducted within a real-world enterprise scenario, Routine significantly increases the execution accuracy in model tool calls, increasing the performance of GPT-4o from 41.1% to 96.3%, and Qwen3-14B from 32.6% to 83.3%. We further constructed a Routine-following training dataset and fine-tuned Qwen3-14B, resulting in an accuracy increase to 88.2% on scenario-specific evaluations, indicating improved adherence to execution plans. In addition, we employed Routine-based distillation to create a scenario-specific, multi-step tool-calling dataset. Fine-tuning on this distilled dataset raised the model's accuracy to 95.5%, approaching GPT-4o's performance. These results highlight Routine's effectiveness in distilling domain-specific tool-usage patterns and enhancing model adaptability to new scenarios. Our experimental results demonstrate that Routine provides a practical and accessible approach to building stable agent workflows, accelerating the deployment and adoption of agent systems in enterprise environments, and advancing the technical vision of AI for Process.

As increasingly powerful generative AI systems are developed, the release method greatly varies. We propose a framework to assess six levels of access to generative AI systems: fully closed; gradual or staged access; hosted access; cloud-based or API access; downloadable access; and fully open. Each level, from fully closed to fully open, can be viewed as an option along a gradient. We outline key considerations across this gradient: release methods come with tradeoffs, especially around the tension between concentrating power and mitigating risks. Diverse and multidisciplinary perspectives are needed to examine and mitigate risk in generative AI systems from conception to deployment. We show trends in generative system release over time, noting closedness among large companies for powerful systems and openness among organizations founded on principles of openness. We also enumerate safety controls and guardrails for generative systems and necessary investments to improve future releases.

Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an external environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this paper we propose CaMeL, a robust defense that creates a protective system layer around the LLM, securing it even when underlying models may be susceptible to attacks. To operate, CaMeL explicitly extracts the control and data flows from the (trusted) query; therefore, the untrusted data retrieved by the LLM can never impact the program flow. To further improve security, CaMeL relies on a notion of a capability to prevent the exfiltration of private data over unauthorized data flows. We demonstrate effectiveness of CaMeL by solving 67% of tasks with provable security in AgentDojo [NeurIPS 2024], a recent agentic security benchmark.

While current Computer Use Agent (CUA) benchmarks measure task completion effectively, they provide limited assessment of enterprise deployment readiness, emphasizing functional correctness over the operational reliability required for production systems. We present UI-CUBE (UiPath Computer Use BEnchmark), a systematic benchmark comprising 226 tasks across two difficulty tiers designed to expose fundamental architectural limitations in current CUAs. Our evaluation covers simple UI interactions (136 tasks) and complex workflows including copy-paste tasks (50 tasks) and enterprise application scenarios (40 tasks), with systematic interface variation coverage, multi-resolution testing and automated validation of task success through the application state. Evaluation of five state-of-the-art models reveals a sharp capability cliff rather than gradual performance degradation. Simple UI interactions achieve 67-85% success rates (compared to 97.9% human performance), but complex workflows drop precipitously to 9-19%. Human evaluators with no prior application experience achieve only 61.2% on complex tasks despite near-perfect performance on simple tasks, establishing realistic performance ceilings. This discontinuous performance pattern -- where agents achieve 68-87% of human performance on simple tasks but only 15-32% on complex workflows -- indicates fundamental architectural limitations in memory management, hierarchical planning, and state coordination rather than incremental capability gaps addressable through better training or prompting. UI-CUBE functions as an enterprise-readiness diagnostic, revealing that while current CUAs can manipulate individual interface elements, they cannot yet function as reliable workflow automation tools. These findings provide architectural insights essential for developing production-ready CUAs capable of managing complex, multi-step enterprise processes.

Large Language Model (LLM) agents can automate cybersecurity tasks and can adapt to the evolving cybersecurity landscape without re-engineering. While LLM agents have demonstrated cybersecurity capabilities on Capture-The-Flag (CTF) competitions, they have two key limitations: accessing latest cybersecurity expertise beyond training data, and integrating new knowledge into complex task planning. Knowledge-based approaches that incorporate technical understanding into the task-solving automation can tackle these limitations. We present CRAKEN, a knowledge-based LLM agent framework that improves cybersecurity capability through three core mechanisms: contextual decomposition of task-critical information, iterative self-reflected knowledge retrieval, and knowledge-hint injection that transforms insights into adaptive attack strategies. Comprehensive evaluations with different configurations show CRAKEN's effectiveness in multi-stage vulnerability detection and exploitation compared to previous approaches. Our extensible architecture establishes new methodologies for embedding new security knowledge into LLM-driven cybersecurity agentic systems. With a knowledge database of CTF writeups, CRAKEN obtained an accuracy of 22% on NYU CTF Bench, outperforming prior works by 3% and achieving state-of-the-art results. On evaluation of MITRE ATT&CK techniques, CRAKEN solves 25-30% more techniques than prior work, demonstrating improved cybersecurity capabilities via knowledge-based execution. We make our framework open source to public https://github.com/NYU-LLM-CTF/nyuctf_agents_craken.

Large Language Models (LLMs) have revolutionized artificial intelligence and machine learning through their advanced text processing and generating capabilities. However, their widespread deployment has raised significant safety and reliability concerns. Established vulnerabilities in deep neural networks, coupled with emerging threat models, may compromise security evaluations and create a false sense of security. Given the extensive research in the field of LLM security, we believe that summarizing the current state of affairs will help the research community better understand the present landscape and inform future developments. This paper reviews current research on LLM vulnerabilities and threats, and evaluates the effectiveness of contemporary defense mechanisms. We analyze recent studies on attack vectors and model weaknesses, providing insights into attack mechanisms and the evolving threat landscape. We also examine current defense strategies, highlighting their strengths and limitations. By contrasting advancements in attack and defense methodologies, we identify research gaps and propose future directions to enhance LLM security. Our goal is to advance the understanding of LLM safety challenges and guide the development of more robust security measures.

The integration of AI agents with Web3 ecosystems harnesses their complementary potential for autonomy and openness yet also introduces underexplored security risks, as these agents dynamically interact with financial protocols and immutable smart contracts. This paper investigates the vulnerabilities of AI agents within blockchain-based financial ecosystems when exposed to adversarial threats in real-world scenarios. We introduce the concept of context manipulation, a comprehensive attack vector that exploits unprotected context surfaces, including input channels, memory modules, and external data feeds. Through empirical analysis of ElizaOS, a decentralized AI agent framework for automated Web3 operations, we demonstrate how adversaries can manipulate context by injecting malicious instructions into prompts or historical interaction records, leading to unintended asset transfers and protocol violations which could be financially devastating. To quantify these vulnerabilities, we design CrAIBench, a Web3 domain-specific benchmark that evaluates the robustness of AI agents against context manipulation attacks across 150+ realistic blockchain tasks, including token transfers, trading, bridges and cross-chain interactions and 500+ attack test cases using context manipulation. We systematically assess attack and defense strategies, analyzing factors like the influence of security prompts, reasoning models, and the effectiveness of alignment techniques. Our findings show that prompt-based defenses are insufficient when adversaries corrupt stored context, achieving significant attack success rates despite these defenses. Fine-tuning-based defenses offer a more robust alternative, substantially reducing attack success rates while preserving utility on single-step tasks. This research highlights the urgent need to develop AI agents that are both secure and fiduciarily responsible.